Computational Models of First Language

合集下载

计算语言学

计算语言学

计算语言学计算语言学(computationallanguagetry)是20世纪80年代后期发展起来的一门语言学新分支。

它将语言的自然属性与功能性计算结合在一起,它从信息论的观点出发,用计算机去处理语言的各种特征和规律,因此也称为信息处理语言学。

目前,这一领域已经成为国际上语言学研究中的一个热点。

因为随着语言理解技术的不断改进,需要处理的信息越来越多,计算机的速度、容量等指标也不断提高,因此对语言理解算法的研究也逐渐引起了人们的重视。

对于计算机而言,从本质上看,它就是一种代码,如同程序员所编写的源程序一样。

但是,计算机是由人来控制的,它可以依据人的指令对数据进行加工和运算,实现特定的功能。

也就是说,计算机只能按照人事先确定的方式来执行,无法根据客观实际情况来作出相应的改变。

1、认知主义和行为主义。

语言学中一般把计算语言学分成两大派别:认知主义和行为主义。

认知主义的主要观点是:语言是知识系统的一部分,语言是我们从事交际活动的工具。

语言是在人脑中表示意义的符号系统,是外界事物的概括的反映,并借助词的形式表现出来。

行为主义的主要观点是:语言是人类交际过程中约定俗成的,符号形式能够描述人们所指的客观世界的思维过程。

人们使用语言来进行交际,是通过手势或面部表情表达他们的内心思想感情的。

他们把人的语言看作是一种人造的符号系统,其作用仅仅是向外部世界传递信息。

2、神经科学和心理语言学。

20世纪70年代以后,计算机和信息论的研究蓬勃兴起,并与人类语言学的研究产生了紧密的联系。

人们逐步发现,计算机的行为模式直接来自人的行为模式,即直接来自于大脑的某些脑区。

人脑的某些脑区被称之为高级认知中心,具有推理、解决问题、记忆和逻辑判断等功能,其主要功能是对外界事物的知觉、学习、记忆、存贮和对事物的归类,并做出适当的行为反应。

计算机是电子设备,电子设备在很大程度上都是按照人们事先制定的程序设计的,这样就保证了整个计算机的操作必须严格按照人们事先确定的规则来执行。

数学技术用于英语学习的英文作文

数学技术用于英语学习的英文作文

数学技术用于英语学习的英文作文Mathematics has long been a subject that is often viewed as separate from language learning, with many students and educators believing that the two disciplines are entirely unrelated. However, in recent years, there has been a growing recognition of the ways in which mathematical techniques can be applied to the study of language, particularly in the context of English language learning.One of the primary ways in which mathematics can be leveraged to support English language learning is through the use of data analysis and statistical techniques. By collecting and analyzing data on language usage, patterns, and trends, educators can gain valuable insights into the ways in which language is acquired and used. For example, by analyzing the frequency and distribution of various grammatical structures, vocabulary words, and idioms, teachers can identify areas of difficulty for language learners and develop targeted instructional strategies to address these challenges.Furthermore, the use of mathematical modeling and simulation can be particularly useful in the context of language learning. By creating computational models of language acquisition and usage, researchers and educators can explore the complex interplay ofvarious factors that influence language learning, such as age, cognitive abilities, cultural background, and exposure to the target language. These models can then be used to inform the development of more effective language learning materials and teaching methods.Another way in which mathematics can be applied to English language learning is through the use of data visualization techniques. By representing language data in visual formats, such as graphs, charts, and diagrams, educators can help learners to better understand and internalize the patterns and structures of the language. This can be particularly useful in the teaching of grammar, where the visual representation of sentence structures and grammatical rules can make complex concepts more accessible and engaging for students.In addition to these more technical applications of mathematics, the discipline can also be used to enhance the overall learning experience for English language learners. For example, by incorporating mathematical problem-solving strategies into language learning activities, teachers can help students to develop critical thinking and analytical skills that are essential for success in both academic and professional settings. Furthermore, the use of numerical data and quantitative reasoning can help to make language learning more concrete and tangible, providing learnerswith a sense of progress and accomplishment as they master new linguistic concepts and skills.Overall, the integration of mathematical techniques and approaches into the field of English language learning represents a promising and exciting area of educational research and practice. By leveraging the power of data analysis, computational modeling, and visual representation, educators can develop more effective and engaging language learning materials and teaching methods, ultimately helping students to achieve greater proficiency and success in their pursuit of English language mastery.。

介绍一位语言学家英语作文

介绍一位语言学家英语作文

介绍一位语言学家英语作文English Response:A linguist is an individual who has a deepunderstanding of language and its intricate workings. They typically possess expertise in specific aspects of language, such as grammar, syntax, phonetics, and pragmatics, among others. Linguists approach language with a scientific perspective, seeking to unravel its systematic nature and identify patterns that govern its structure and usage.Linguists engage in various research activities, including analyzing linguistic data, studying language change, and exploring the relationships between different languages. They employ a combination of qualitative and quantitative methods, utilizing both descriptive and analytical approaches to advance our understanding of language. Their research contributes significantly to awide range of disciplines, including social sciences, humanities, computer science, and even healthcare.The field of linguistics encompasses a broad spectrumof subfields, each with its unique focus. For instance, sociolinguistics examines the relationship between language and society, while psycholinguistics investigates the psychological processes involved in language production and comprehension. Computational linguistics, on the other hand, explores the intersection of language and technology, developing computational models and tools for language processing.Linguists play a crucial role in various professions, including education, research, and language policy. Theyare often employed as teachers, researchers, or language consultants, using their expertise to educate students, conduct research, and inform language-related policies and practices. Their work has a significant impact on our understanding of language, communication, and culture, shaping how we interact with the world around us.中文回答:语言学家是对语言及其复杂运作有深刻理解的人。

大语言模型的训练流程

大语言模型的训练流程

大语言模型的训练流程Training a large language model is a complex and time-consuming process that involves multiple steps and considerations. The first step in training a large language model is to gather and pre-process a massive amount of text data. This data is essential for training the model to understand and generate human-like language. In the case of just an English-speaking language model, this would likely involve compiling a diverse range of text from books, articles, websites, and other sources. The more varied and extensive the data, the better the model can learn to generate natural and coherent language.训练一个大型语言模型是一个复杂而耗时的过程,涉及多个步骤和考虑因素。

训练大语言模型的第一步是收集和预处理大量的文本数据。

这些数据对于训练模型理解和生成类似人类语言至关重要。

对于一个只有英语的语言模型来说,这可能涉及从书籍、文章、网站和其他来源编制多样化的文本。

数据越多样化和广泛,模型学习生成自然和连贯语言的能力就越好。

Once the text data is gathered, it needs to be pre-processed to remove any irrelevant or problematic content and to format it in a way that is suitable for training the language model. This may involvetasks such as tokenization, where the text is broken down into smaller units like words or characters, and filtering out any rare or non-standard terms that could negatively impact the model's learning process. Additionally, the data may need to be split into training, validation, and testing sets to evaluate the model's performance.一旦文本数据被收集,就需要对其进行预处理,以删除任何不相关或有问题的内容,并以适合训练语言模型的方式进行格式化。

语言学第六章Part One

语言学第六章Part One

What that? Andrew want that. Not sit here.

Embed one constituent inside another:

Give doggie paper. Give big doggie paper.
Teaching points
1. What is cognition? 2. What is psycholinguistics?
Commonalities between language and cognition:

childhood cognitive development (Piaget):


[haj]: hi [s]: spray [sr]: shirt, sweater [sæ:]: what’s that?/ hey, look! [ma]: mommy [dæ ]: daddy
Fromkin,V., Rodman, R., & Hymans, N. (2007)An Introduction to Language (8th Ed.). Singapore/Beijing: Thompson/PUP
Two-word stage: around 18m
Child utterance Want cookie More milk Joe see My cup Mature speaker I want a cookie I want some more milk I (Joe) see you This is my cup Purpose Request Request Informing Warning



1. Diaries-Charles Darwin; 2. Tape recorders; 3. Videos and computers. Eg. Dr. Deb Roy (MIT)

The-Role-of-The-First-Language

The-Role-of-The-First-Language

2、regarding the feasibility of comparing languages and the methodology of Contrastive Analysis.
3、reservations about whether Contrastive Analysis had anything relevant to offer to language teaching
Theoretical criticisms
➢The issues will be considered
(1) The attack on “Verbal Behaviors”
(2) The nature of the relationship between “difficulty” and “error”
目录
A multi-factor approach
L1 interference as a learner strategy
Contrastive Analysis
Contrastive pragmatics
Summary and conclusion
1 Introduction
Two popular belief
Empirical research and the predictability of error
➢Four causes of learner error:
1、the learner does not know the structural pattern and so makes a random response 2、 the correct model has been insufficiently practiced 3、distortion may be induced by the first language 4、the student may follow a general rule which is not applicable in particular instance

大语言模型核心技术介绍

大语言模型核心技术介绍

大语言模型核心技术介绍Language models are a type of artificial intelligence system that has gained significant traction in recent years. These models are designed to process and generate human language, with the goal of improving natural language processing tasks such as translation, text generation, and question answering. Language models have become increasingly sophisticated, with the most recent advancements in large language models being some of the most significant in the field.语言模型是一种人工智能系统,近年来取得了显著的进展。

这些模型旨在处理和生成人类语言,以改进自然语言处理任务,如翻译、文本生成和问答。

语言模型变得越来越复杂,最近大语言模型的最新进展是该领域最重要的之一。

One of the key components of large language models is the use of neural networks. These networks are designed to mimic the way the human brain processes information, allowing them to learn from large amounts of data and improve their performance over time. By using neural networks, language models are able to understand thecomplex patterns and structures within human language, leading to more accurate and natural language generation.大型语言模型的关键组成部分之一是使用神经网络。

(完整版)胡壮麟语言学教程笔记、重点全解

(完整版)胡壮麟语言学教程笔记、重点全解

《语言学教程》重难点学习提示第一章语言的性质语言的定义:语言的基本特征(任意性、二重性、多产性、移位、文化传递和互换性);语言的功能(寒暄、指令、提供信息、询问、表达主观感情、唤起对方的感情和言语行为);语言的起源(神授说,人造说,进化说)等。

第二章语言学语言学定义;研究语言的四大原则(穷尽、一致、简洁、客观);语言学的基本概念(口语与书面语、共时与历时、语言与言学、语言能力与言行运用、语言潜势与语言行为);普通语言学的分支(语音、音位、语法、句法、语义);;语言学的应用(语言学与语言教学、语言与社会、语言与文字、语言与心理学、人类语言学、神经语言学、数理语言学、计算语言学)等。

第三章语音学发音器官的英文名称;英语辅音的发音部位和发音方法;语音学的定义;发音语音学;听觉语音学;声学语音学;元音及辅音的分类;严式与宽式标音等。

第四章音位学音位理论;最小对立体;自由变异;互补分布;语音的相似性;区别性特征;超语段音位学;音节;重音(词重音、句子重音、音高和语调)等。

第五章词法学词法的定义;曲折词与派生词;构词法(合成与派生);词素的定义;词素变体;自由词素;粘着词素(词根,词缀和词干)等。

第六章词汇学词的定义;语法词与词汇词;变词与不变词;封闭词与开放词;词的辨认;习语与搭配。

第七章句法句法的定义;句法关系;结构;成分;直接成分分析法;并列结构与从属结构;句子成分;范畴(性,数,格);一致;短语,从句,句子扩展等。

第八章语义学语义的定义;语义的有关理论;意义种类(传统、功能、语用);里奇的语义分类;词汇意义关系(同义、反义、下义);句子语义关系。

第九章语言变化语言的发展变化(词汇变化、语音书写文字、语法变化、语义变化);第十章语言、思维与文化语言与文化的定义;萨丕尔-沃夫假说;语言与思维的关系;语言与文化的关系;中西文化的异同。

第十一章语用学语用学的定义;语义学与语用学的区别;语境与意义;言语行为理论(言内行为、言外行为和言后行为);合作原则。

Computational linguistics

Computational linguistics


分支领域(Subfields) 计算语言学可以分为几个主要领域,根 据语言处理的介质,是口语的还是文本 的;以及任务的执行,是分析语言的, 还是综合语言(生成)的。



Speech recognition and speech synthesis deal with how spoken language can be understood or created using computers. Parsing and generation are subdivisions of computational linguistics dealing respectively with taking language apart and putting it together. Machine translation remains the subdivision of computational linguistics dealing with having computers translate between languages.


为了把一种语言翻译成另一种语言,人 们注意到,必须理解两种语言的语法, 包括两种语言的词法(关于词形式的语 法)和句法(关于句子结构的语法)。 要理解句法,人们还不得不理解语义和 辞典(或词汇),甚至还不得不理解语 言使用即语用的某些东西。 因而,语言之间的翻译从何入手,这牵 涉到致力于理解如何用计算机表示及处 理自然语言的整个领域范畴。


Computational linguistics as a field predates artificial intelligence, a field under which it is often grouped. Computational linguistics originated with efforts in the United States in the 1950s to use computers to automatically translate texts from foreign languages, particularly Russian scientific journals, into English.

潮流计算英语

潮流计算英语

潮流计算英语Title: The Trend of Computational EnglishComputational English, the fusion of computational linguistics and English language studies, has emerged as a burgeoning field in recent years, propelled by advancements in artificial intelligence and natural language processing. This interdisciplinary domain encompasses various aspects of language analysis, generation, and application, revolutionizing how we perceive and interact with English. In this essay, we delve into the key components and evolving trends within computational English, exploring its impact on linguistics, education, communication, and beyond.At its core, computational English leverages computational techniques to analyze, interpret, and generate English language data. Natural language processing (NLP) algorithms play a pivotal role in tasks such as textsummarization, sentiment analysis, and machine translation. These algorithms rely on linguistic principles to decipher the nuances of English syntax, semantics, and pragmatics, enabling machines to comprehend and produce human-like language output.One of the prominent trends in computational English is the development of intelligent tutoring systems (ITS)tailored for language learning. These systems employ NLP algorithms to provide personalized feedback, adaptive learning paths, and interactive exercises to enhancelearners' proficiency in English. By leveraging machine learning models, ITS can adapt to individual learning styles and track progress over time, offering a dynamic and immersive learning experience.Moreover, computational English intersects with sociolinguistics to analyze language variation and change in digital communication platforms. Social media, online forums,and messaging apps serve as rich sources of linguistic data, reflecting contemporary language usage, slang, and cultural trends. Computational linguists utilize techniques such as sentiment analysis and network analysis to uncover patterns in online discourse, shedding light on evolving linguistic norms and communicative strategies.The rise of computational creativity has also spurred innovation in English language generation. Generative models, such as recurrent neural networks (RNNs) and transformer architectures, can produce coherent and contextually relevant English text, ranging from poetry and storytelling to automated content generation. These models learn from vast corpora of text data, capturing the stylistic nuances and thematic patterns prevalent in English literature and discourse.Furthermore, computational English facilitates the development of assistive technologies for individuals withlanguage-related disabilities. Speech recognition systems, text-to-speech synthesis, and augmentative communication devices empower users to overcome communication barriers and access information in real-time. These assistive technologies leverage advanced NLP techniques to interpret spoken or written input and generate appropriate responses, fostering inclusivity and accessibility in diverse linguistic contexts.In the realm of academic research, computational English serves as a catalyst for interdisciplinary collaboration between linguists, computer scientists, psychologists, and educators. Cross-disciplinary initiatives explore innovative methodologies for corpus linguistics, discourse analysis, and psycholinguistic experiments, leveraging computational tools to address fundamental questions about language structure, acquisition, and usage.Looking ahead, the future of computational English holds immense promise and potential. Advancements in deep learning,cognitive computing, and human-computer interaction will continue to shape the landscape of linguistic research and technological innovation. As computational capabilities evolve, so too will our understanding of language dynamics and the ways in which technology can augment linguistic creativity, communication, and comprehension.In conclusion, computational English represents a convergence of computational methodologies and linguistic inquiry, redefining how we analyze, generate, and utilize English language data. From intelligent tutoring systems to assistive technologies and computational creativity, this interdisciplinary field permeates diverse domains, driving innovation and insights at the intersection of language and technology. As we navigate the complexities of linguistic diversity and digital communication, computational English remains at the forefront of transformative research and practical applications, shaping the future of language in the digital age.。

胡的语言学术语英汉对照翻译表

胡的语言学术语英汉对照翻译表

胡的语言学术语英汉对照翻译表(很全的)1. 语言的普遍特征:任意性arbitrariness双层结构duality 既由声音和意义结构多产性productivity移位性displacement:我们能用语言可以表达许多不在场的东西文化传播性cultural transmission2。

语言的功能:传达信息功能informative人济功能:interpersonal行事功能:Performative表情功能:Emotive寒暄功能:Phatic娱乐功能recreatinal元语言功能metalingual3. 语言学linguistics:包括六个分支语音学Phonetics音位学phonology形态学Morphology句法学syntax语义学semantics语用学pragmatics4. 现代结构主义语言学创始人:Ferdinand de saussure提出语言学中最重要的概念对之一:语言与言语language and parole ,语言之语言系统的整体,言语则只待某个个体在实际语言使用环境中说出的具体话语5. 语法创始人:Noam Chomsky提出概念语言能力与语言运用competence and performance1. Which of the following statements can be used to describe displacement. one of the unique properties of language:a. we can easily teach our children to learn a certain languageb. we can use both 'shu' and 'tree' to describe the same thing.c. we can u se language to refer to something not presentd. we can produce sentences that have never been heard before.2.What is the most important function of language?a. interpersonalb. phaticc. informatived.metallingual3.The function of the sentence "A nice day, isn't it ?"is __a informativeb. phaticc. directived. performative4.The distinction between competence and performance is proposed by __a saussureb. hallidayc. chomskyd. the prague school5. Who put forward the distinction between language and parole?a. saussureb. chomskyc. hallidayd anomymous第二节语音学1.发音器官由声带the vocal cords和三个回声腔组成2.辅音consonant:there is an obstruction of the air stream at some point of the vocal tract.3.辅音的发音方式爆破音complete obstruction鼻音nasals破裂音plosives部分阻塞辅音partial obstruction擦音fricatives破擦音affricates等4.辅音清浊特征voicing辅音的送气特征aspiration5.元音vowel分类标准舌翘位置,舌高和嘴唇的形状6双元音diphthongs,有元音过渡vowel glides1. Articulatory phonetics mainly studies __.a. the physical properties of the sounds produced in speechb. the perception of soundsc. the combination of soundsd. the production of sounds2. The distinction between vowel s and consonants lies in __a. the place of articulationb.the obstruction f airstreamc. the position of the tongued. the shape of the lips3. What is the common factor of the three sounds: p, k ta. voicelessb. spreadc.voicedd.nasal4. What phonetic feature distinguish the p in please and the p in speak?a. voicingb. aspirationc.roundnessd. nasality5.Which of the following is not a distinctive feature in English?a. voicingb.nasalc. approximationd. aspiration6.The phonological features of the consonant k are __a. voiced stopb. voiceless stopc. voiced fricatived. voiceless fricative7.p is divverent from k in __a. the manner of articulationb. the shape of the lipsc. the vibration of the vocal cordsd.the palce of articualtion8.Vibration of the vocal cords results in __a. aspirationb.nasalityc. obstructiond. voicing第三节音位学phonology1.音位学与语音学的区别:语音学着重于语音的自然属性,主要关注所有语言中人可能发出的所有声音;音位学则强调语音的社会功能,其对象是某一种语言中可以用来组合成词句的那些语音。

Grammar语法的定义

Grammar语法的定义

GrammarFor the rules of the English language, see English grammar. For the topic in mathematics, logic, and theoretical computer science, see Formal grammar.Not to be confused with Grammer or Krammer.LinguisticsTheoretical linguisticsCognitive linguisticsGenerative linguisticsFunctional theories of grammarQuantitative linguisticsPhonology ·Morphology ·Morphophonology ·Syntax ·Lexis ·Sem antics ·Pragmatics ·Graphemics ·Orthography ·Semiotics Descriptive linguisticsAnthropological linguisticsComparative linguisticsHistorical linguisticsEtymology ·Graphetics ·Phonetics ·SociolinguisticsApplied andexperimental linguisticsComputational linguisticsEvolutionary linguisticsForensic linguisticsInternet linguisticsLanguage acquisitionLanguage assessmentLanguage developmentLanguage educationLinguistic anthropology NeurolinguisticsPsycholinguisticsSecond-language acquisitionRelated articlesHistory of linguisticsLinguistic prescriptionList of linguistsList of unsolved problems in linguisticsPortalv ·t ·eIn linguistics, grammar is the set of structural rules that governs the composition of clauses, phrases, and words in any given natural language. The term refers also to the study of such rules, and this field includes morphology, syntax, and phonology, often complemented by phonetics, semantics, and pragmatics. Linguists do not normally use the term to refer to orthographical rules, although usage books and style guides that call themselves grammars may also refer to spelling and punctuation.[citation needed]Contents [hide]1 Use of the term2 Etymology3 History4 Development of grammars5 Grammar frameworks6 Education7 See also8 Notes and references9 External links[edit] Use of the termThe term grammar is often used bynon-linguists with a very broad meaning. As Jeremy Butterfield puts it: "Grammar is often a generic way of referring to any aspect of English that people object to."[1] However, linguists use it in a much more specific sense. Speakers of a language have in their heads a set of rules[2] for using that language. This is a grammar, and—at least in the case of one's native language—the vast majority of the information in it is acquired not by conscious study or instruction, but by observing other speakers; much of this work is done during infancy. Language learning later in life, of course, may involve a greater degree of explicit instruction.[3]The term "grammar" can also be used to describe the rules that govern the linguistic behaviour of a group of speakers. The term "English grammar", therefore, may have several meanings. It may refer to the whole of English grammar—that is, to the grammars of all the speakers of the language—in which case, the term encompasses a great deal of variation.[4] Alternatively, it may refer only to what is common to the grammars of all, or of the vast majority of English speakers (such as subject–verb–object word order in simple declarative sentences). Or it may refer to the rules ofa particular, relatively well-defined variety of English (such as Standard English)."An English grammar" is a specific description, study or analysis of such rules. A reference book describing the grammar of a language is called a "reference grammar" or simply "a grammar." A fully explicit grammar that exhaustively describes the grammatical constructions of a language is called a descriptive grammar. This kind of linguistic description contrasts with linguistic prescription, an attempt to discourage or suppress some grammatical constructions, while promoting others. For example, preposition stranding occurs widely in Germanic languages and has a long history in English. John Dryden, however, objected to it (without explanation),[5] leading other English speakers to avoid the construction and discourage its use.[6][edit] EtymologyFurther information: GraphemeThe word grammar derives from Greek γραμματικὴτέχνη (grammatikē technē), which means "art of letters", from γράμμα (gramma), "letter", itself from γράφειν (graphein), "to draw, to write".[7][edit] HistoryFurther information: History of linguisticsThe first systematic grammars originated in Iron Age India, with Yaska (6th c. BC), Pāṇini (4th c. BC) and his commentators Pingala (ca. 200 BC), Katyayana, and Patanjali (2nd c. BC). In the West, grammar emerged as a discipline in Hellenism from the 3rd c. BC forward with authors like Rhyanus and Aristarchus of Samothrace, the oldest extant work being the Art of Grammar (ΤέχνηΓραμματική), attributed to Dionysius Thrax (ca. 100 BC). Latin grammar developed by following Greek models from the 1st century BC, due to the work of authors such as Orbilius Pupillus, Remmius Palaemon, Marcus Valerius Probus, Verrius Flaccus, and Aemilius Asper.Tolkāppiyam is the earliest Tamil grammar; it has been dated variously between 1st CE and 10th CE.A grammar of Irish originated in the 7th century with the Auraicept na n-Éces.Arabic grammar emerged with Abu al-Aswad al-Du'ali from the 7th century who in-turn was taught the discipline by Ali ibn Abitalib, the fourth historical caliph of Islam and first Imam for Shi'i Muslims.The first treatises on Hebrew grammar appeared in the High Middle Ages, in the context of Mishnah (exegesis of the Hebrew Bible). The Karaite tradition originated in Abbasid Baghdad. The Diqduq (10th century) is one of the earliest grammatical commentaries on the Hebrew Bible.[8] Ibn Barun in the 12th century compares the Hebrew language with Arabic in the Islamic grammatical tradition.[9]Belonging to the trivium of the seven liberal arts, grammar was taught as a core discipline throughout the Middle Ages, following the influence of authors from Late Antiquity, such as Priscian. Treatment of vernaculars began gradually during the High Middle Ages, with isolated works such as the First Grammatical Treatise, but became influential only in the Renaissance and Baroque periods. In 1486, Antonio de Nebrija published Las introduciones Latinas contrapuesto el romance al Latin, and the first Spanish grammar, Gramática de la lengua castellana, in 1492. During the 16th century Italian Renaissance, the Questione della lingua was the discussion on the status and ideal form of the Italian language, initiated by Dante'sde vulgari eloquentia (Pietro Bembo, Prose della volgar lingua Venice 1525). The first grammar of Slovene language was written in 1584 by Adam Bohorič.Grammars of non-European languages began to be compiled for the purposes of evangelization and Bible translation from the 16th century onward, such as Grammatica o Arte de la Lengua General de los Indios de los Reynos del Perú (1560), and a Quechua grammar by Fray Domingo de Santo Tomás.In 1643 there appeared Ivan Uzhevych's Grammatica sclavonica and, in 1762, the Short Introduction to English Grammar of Robert Lowth was also published. The Grammatisch-Kritisches Wörterbuch der hochdeutschen Mundart, a High German grammar in five volumes by Johann Christoph Adelung, appeared as early as 1774.From the latter part of the 18th century, grammar came to be understood as a subfield of the emerging discipline of modern linguistics. The Serbian grammar by Vuk S tefanović Karadžić arrived in 1814, while the Deutsche Grammatik of the Brothers Grimm was first published in 1818. The Comparative Grammar ofFranz Bopp, the starting point of modern comparative linguistics, came out in 1833.[edit] Development of grammarsMain article: Historical linguisticsGrammars evolve through usage and also due to separations of the human population. With the advent of written representations, formal rules about language usage tend to appear also. Formal grammars are codifications of usage that are developed by repeated documentation over time, and by observation as well. As the rules become established and developed, the prescriptive concept of grammatical correctness can arise. This often creates a discrepancy between contemporary usage and that which has been accepted, over time, as being correct. Linguists tend to view prescriptive grammars as having little justification beyond their authors' aesthetic tastes, although style guides may give useful advice about standard language employment, based on descriptions of usage in contemporary writings of the same language. Linguistic prescriptions also form part of the explanation for variation in speech, particularly variation in the speech of an individual speaker (an explanation, for example, for why some people say, "I didn't donothing"; some say, "I didn't do anything"; and some say one or the other depending on social context).The formal study of grammar is an important part of educationfor children from a young age through advanced learning, though the rules taught in schools are not a "grammar" in the sense most linguists use the term, particularly as they are often prescriptive rather than descriptive.Constructed languages (also called planned languages or conlangs) are more common in the modern day. Many have been designed to aid human communication (for example, naturalistic Interlingua, schematic Esperanto, and the highly logic-compatible artificial language Lojban). Each of these languages has its own grammar.Syntax refers to linguistic structure above the word level (e.g. how sentences are formed)—though without taking into account intonation, which is the domain of phonology. Morphology, by contrast, refers to structure at and below the word level (e.g. how compound words are formed), but above the level of individual sounds, which, like intonation, are in the domain of phonology.[10] No clear line can be drawn, however, between syntax andmorphology. Analytic languages use syntax to convey information that is encoded via inflection in synthetic languages. In other words, word order is not significant and morphology is highly significant in a purely synthetic language, whereas morphology is not significant and syntax is highly significant in an analytic language. Chinese and Afrikaans, for example, are highly analytic, and meaning is therefore very context-dependent. (Both do have some inflections, and have had more in the past; thus, they are becoming even less synthetic and more "purely" analytic over time.) Latin, which is highly synthetic, uses affixes and inflections to convey the same information that Chinese does with syntax. Because Latin words are quite (though not completely) self-contained, an intelligible Latin sentence can be made from elements that are placed in a largely arbitrary order. Latin has a complex affixation and simple syntax, while Chinese has the opposite.[edit] Grammar frameworksMain article: Grammar framework Various "grammar frameworks" have been developed in theoretical linguistics since the mid 20th century, in particular under the influence of the idea of a "universal grammar" in the United States. Of these, the main divisions are:Transformational grammar (TG)Systemic functional grammar (SFG)Principles and Parameters Theory (P&P)Lexical-functional Grammar (LFG)Generalized Phrase Structure Grammar (GPSG)Head-Driven Phrase Structure Grammar (HPSG)Dependency grammars (DG)Role and reference grammar (RRG)[edit] EducationFurther information: orthographyPrescriptive grammar is taught in primary school (elementary school). The term "grammar school" historically refers to a school teaching Latin grammar to future Roman citizens, orators, and, later, Catholic priests. In its earliest form, "grammar school" referred to a school that taught students to read, scan, interpret, and declaim Greek and Latin poets (including Homer, Virgil, Euripides, Ennius, and others). These should not be confused with the related, albeit distinct, modern British grammar schools.A standard language is a particular dialect of a language that is promoted above other dialects in writing, education, and broadly speaking in the public sphere; it contrasts with vernacular dialects, which may be the objects of study in descriptive grammar but whichare rarely taught prescriptively. The standardized "first language" taught in primary education may be subject to political controversy, since it establishes a standard defining nationality or ethnicity.Recently, efforts have begun to update grammar instruction in primary and secondary education. The primary focus has been to prevent the use of outdated prescriptive rules in favor of more accurate descriptive ones and to change perceptions about relative "correctness" of standard forms in comparison to non standard dialects.The pre-eminence of Parisian French has reigned largely unchallenged throughout the history of modern French literature. Standard Italian is not based on the speech of the capital, Rome, but on the speech of Florence because of the influence Florentines had on early Italian literature. Similarly, standard Spanish is not based on the speech of Madrid, but on the one of educated speakers from more northerly areas like Castile and León. In Argentina and Uruguay the Spanish standard is based on the local dialects of Buenos Aires and Montevideo (Rioplatense Spanish). Portuguese has for now two official written standards, respectively BrazilianPortuguese and European Portuguese, but in a short term it will have a unified orthography.[11]The Serbian language is divided in a similar way; Serbia and the Republika Srpska use their own separate standards. The existence of a third standard is a matter of controversy, some consider Montenegrin as a separate language, and some think it's merely another variety of Serbian.Norwegian has two standards, Bokmål and Nynorsk, the choice between which is subject to controversy: Each Norwegian municipality can declare one of the two its official language, or it can remain "language neutral". Nynorsk is endorsed by a minority of 27 percent of the municipalities. The main language used in primary schools normally follows the official language of its municipality, and is decided by referendum within the local school district. Standard German emerged out of the standardized chancellery use of High German in the 16th and 17th centuries. Until about 1800, it was almost entirely a written language, but now it is so widely spoken that most of the former German dialects are nearly extinct.Standard Chinese has official status as the standard spoken form of the Chinese language in the People's Republic of China (PRC), the Republic of China (ROC) and the Republic of Singapore. Pronunciation of Standard Chinese is based on the Beijing dialect of Mandarin Chinese, while grammar and syntax are based on modern vernacular written Chinese. Modern Standard Arabic is directly based on Classical Arabic, the language of the Qur'an. The Hindustani language has two standards, Hindi and Urdu.In the United States, the Society for the Promotion of Good Grammar designated March 4 as National Grammar Day in 2008.[12][edit] See alsoCategory:Grammars of specific languagesAmbiguous grammarGovernment and bindingHarmonic GrammarHigher order grammarGrammemeLinguistic typologyList of linguistsParagrammatismSyntaxUniversal grammarUsage[edit] Notes and references1.^ Jeremy Butterfield, (2008) Damp Squid: The English Language Laid Bare, Oxford University Press, Oxford. 978-0-19-923906. p. 142.2.^ Traditionally, the mental information used to produce and process linguistic utterances is referred to as "rules." However, other frameworks employ different terminology, with theoretical implications. Optimality theory, for example, talks in terms of "constraints", while Construction grammar, Cognitive grammar, and other "usage-based" theories make reference to patterns, constructions, and "schemata"3.^ O'Grady, William; Dobrovolsky, Michael; Katamba, Francis (1996). Contemporary Linguistics: An Introduction. Harlow, Essex: Longman. pp. 4–7; 464–539./books?id=djhsAAAAIAAJ&q=Contempo rary+Linguistics&dq=Contemporary+Linguistics.4.^ Holmes, Janet (2001). An Introduction to Sociolinguistics (second ed.). Harlow, Essex: Longman. pp. 73–94./books?id=qjdqxecifHcC&printsec=frontco ver&dq=Introduction+to+Sociolinguistics+Holmes. ; for morediscussion of sets of grammars as populations, see: Croft, William (2000). Explaining Language Change: An Evolutionary Approach. Harlow, Essex: Longman. pp. 13–20./books?id=5_Ka7zLl9HQC&printsec=fron tcover&dq=Explaining+Language+Change+Croft.5.^ Rodney Huddleston and Geoffrey K. Pullum, 2002, The Cambridge Grammar of the English Language. Cambridge (UK): Cambridge University Press, p. 627f.6.^ Lundin, Leigh (2007-09-23). "The Power of Prepositions". On Writing. Cairo: Criminal Brief. /?p=216.7.^ Harper, Douglas, "Grammar", Online Etymological Dictionary, /index.php?term=grammar, retrieved 8 April 20108.^ G. Khan, J. B. Noah, The Early Karaite Tradition of Hebrew Grammatical Thought (2000)9.^ Pinchas Wechter, Ibn Barūn's Arabic Works on Hebrew Grammar and Lexicography (1964)10.^ Gussenhoven, Carlos; Jacobs, Haike (2005). Understanding Phonology (second ed.). London: Hodder Arnoldd./books?id=gHp_QgAACAAJ&dq=Underst anding+Phonology&cd=1.11.^ [1]12.^ National Grammar DayAmerican Academic Press, The (ed.). William Strunk, Jr., et al. The Classics of Style: The Fundamentals of Language Style From Our American Craftsmen. Cleveland: The American Academic Press, 2006. ISBN 0-9787282-0-3.Rundle, Bede. Grammar in Philosophy. Oxford: Clarendon Press; New York: Oxford University Press, 1979. ISBN 0-19-824612-9.[edit] External links Look up grammar in Wiktionary, the free dictionary.Archibald Henry Sayce (1911). "Grammar". In Chisholm, Hugh. Encyclopædia Britannica (11th ed.). Cambridge University Press.GrammarBank : Grammar rules explanations with examples and exercises onlineThe syntax of natural language: An online introduction using the Trees program -- Beatrice Santorini & Anthony Kroch, University of Pennsylvania, 2007The Grammar Vandal (Funny, informative blog that fixes bad grammar.)The "Blog" of "Unnecessary" Quotes (Another educational, still funny poke at people who incorrectly use quote marks.)。

An introduction to the theory of computation

An introduction to the theory of computation

theory of computation
1-9
Why and how ?
Why we study theory of computation ? — Theory of computation is the foundation of Theoretical Computer Science (TCS) — Can provide very useful techniques in some areas — Reflects human being’s intelligence — ...
theory of computation
1-8
About input/output form
What computing devices deal with is input Input is always the string (this is the part of
preliminaries, chapter 0 ) — Set — Alphabet — symbol — Sequence (string, word) There is a question that need to be aware of — how to encode other objects into strings.
Post (1944) studies degrees of unsolvability Matjasevic (1970) solves Hilbert’s 10th problem about the
undecidability of Diophantine equations
Cook (1971) introduces the complexity classes P and NP

参考文献(人工智能)

参考文献(人工智能)

参考文献(人工智能)曹晖目的:对参考文献整理(包括摘要、读书笔记等),方便以后的使用。

分类:粗分为论文(paper)、教程(tutorial)和文摘(digest)。

0介绍 (1)1系统与综述 (1)2神经网络 (2)3机器学习 (2)3.1联合训练的有效性和可用性分析 (2)3.2文本学习工作的引导 (2)3.3★采用机器学习技术来构造受限领域搜索引擎 (3)3.4联合训练来合并标识数据与未标识数据 (5)3.5在超文本学习中应用统计和关系方法 (5)3.6在关系领域发现测试集合规律性 (6)3.7网页挖掘的一阶学习 (6)3.8从多语种文本数据库中学习单语种语言模型 (6)3.9从因特网中学习以构造知识库 (7)3.10未标识数据在有指导学习中的角色 (8)3.11使用增强学习来有效爬行网页 (8)3.12★文本学习和相关智能A GENTS:综述 (9)3.13★新事件检测和跟踪的学习方法 (15)3.14★信息检索中的机器学习——神经网络,符号学习和遗传算法 (15)3.15用NLP来对用户特征进行机器学习 (15)4模式识别 (16)4.1JA VA中的模式处理 (16)0介绍1系统与综述2神经网络3机器学习3.1 联合训练的有效性和可用性分析标题:Analyzing the Effectiveness and Applicability of Co-training链接:Papers 论文集\AI 人工智能\Machine Learning 机器学习\Analyzing the Effectiveness and Applicability of Co-training.ps作者:Kamal Nigam, Rayid Ghani备注:Kamal Nigam (School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, knigam@)Rayid Ghani (School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213 rayid@)摘要:Recently there has been significant interest in supervised learning algorithms that combine labeled and unlabeled data for text learning tasks. The co-training setting [1] applies todatasets that have a natural separation of their features into two disjoint sets. We demonstrate that when learning from labeled and unlabeled data, algorithms explicitly leveraging a natural independent split of the features outperform algorithms that do not. When a natural split does not exist, co-training algorithms that manufacture a feature split may out-perform algorithms not using a split. These results help explain why co-training algorithms are both discriminativein nature and robust to the assumptions of their embedded classifiers.3.2 文本学习工作的引导标题:Bootstrapping for Text Learning Tasks链接:Papers 论文集\AI 人工智能\Machine Learning 机器学习\Bootstrap for Text Learning Tasks.ps作者:Rosie Jones, Andrew McCallum, Kamal Nigam, Ellen Riloff备注:Rosie Jones (rosie@, 1 School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213)Andrew McCallum (mccallum@, 2 Just Research, 4616 Henry Street, Pittsburgh, PA 15213)Kamal Nigam (knigam@)Ellen Riloff (riloff@, Department of Computer Science, University of Utah, Salt Lake City, UT 84112)摘要:When applying text learning algorithms to complex tasks, it is tedious and expensive to hand-label the large amounts of training data necessary for good performance. This paper presents bootstrapping as an alternative approach to learning from large sets of labeled data. Instead of a large quantity of labeled data, this paper advocates using a small amount of seed information and alarge collection of easily-obtained unlabeled data. Bootstrapping initializes a learner with the seed information; it then iterates, applying the learner to calculate labels for the unlabeled data, and incorporating some of these labels into the training input for the learner. Two case studies of this approach are presented. Bootstrapping for information extraction provides 76% precision for a 250-word dictionary for extracting locations from web pages, when starting with just a few seed locations. Bootstrapping a text classifier from a few keywords per class and a class hierarchy provides accuracy of 66%, a level close to human agreement, when placing computer science research papers into a topic hierarchy. The success of these two examples argues for the strength of the general bootstrapping approach for text learning tasks.3.3 ★采用机器学习技术来构造受限领域搜索引擎标题:Building Domain-specific Search Engines with Machine Learning Techniques链接:Papers 论文集\AI 人工智能\Machine Learning 机器学习\Building Domain-Specific Search Engines with Machine Learning Techniques.ps作者:Andrew McCallum, Kamal Nigam, Jason Rennie, Kristie Seymore备注:Andrew McCallum (mccallum@ , Just Research, 4616 Henry Street Pittsburgh, PA 15213)Kamal Nigam (knigam@ , School of Computer Science, Carnegie Mellon University Pittsburgh, PA 15213)Jason Rennie (jr6b@)Kristie Seymore (kseymore@)摘要:Domain-specific search engines are growing in popularity because they offer increased accuracy and extra functionality not possible with the general, Web-wide search engines. For example, allows complex queries by age-group, size, location and cost over summer camps. Unfortunately these domain-specific search engines are difficult and time-consuming to maintain. This paper proposes the use of machine learning techniques to greatly automate the creation and maintenance of domain-specific search engines. We describe new research in reinforcement learning, information extraction and text classification that enables efficient spidering, identifying informative text segments, and populating topic hierarchies. Using these techniques, we have built a demonstration system: a search engine forcomputer science research papers. It already contains over 50,000 papers and is publicly available at ....采用多项Naive Bayes 文本分类模型。

语言学专业术语

语言学专业术语

1. 语言的普遍特征:任意性arbitrariness双层结构duality 既由声音和意义结构多产性productivity移位性displacement:我们能用语言可以表达许多不在场的东西文化传播性cultural transmission2。

语言的功能:传达信息功能informative人济功能:interpersonal行事功能:Performative表情功能:Emotive寒暄功能:Phatic娱乐功能recreatinal元语言功能metalingual3. 语言学linguistics:包括六个分支语音学Phonetics音位学phonology形态学Morphology句法学syntax语义学semantics语用学pragmatics4. 现代结构主义语言学创始人:Ferdinand de saussure提出语言学中最重要的概念对之一:语言与言语language and parole ,语言之语言系统的整体,言语则只待某个个体在实际语言使用环境中说出的具体话语5. 语法创始人:Noam Chomsky提出概念语言能力与语言运用competence and performance1. Which of the following statements can be used to describe displacement. one of the unique properties of language:a. we can easily teach our children to learn a certain languageb. we can use both 'shu' and 'tree' to describe the same thing.c. we can u se language to refer to something not presentd. we can produce sentences that have never been heard before.2.What is the most important function of language?a. interpersonalb. phaticc. informatived.metallingual3.The function of the sentence "A nice day, isn't it ?"is __a informativeb. phaticc. directived. performative4.The distinction between competence and performance is proposed by __a saussurec. chomskyd. the prague school5. Who put forward the distinction between language and parole?a. saussureb. chomskyc. hallidayd anomymous第二节语音学1.发音器官由声带the vocal cords和三个回声腔组成2.辅音consonant:there is an obstruction of the air stream at some point of the vocal tract.3.辅音的发音方式爆破音complete obstruction鼻音nasals破裂音plosives部分阻塞辅音partial obstruction擦音fricatives破擦音affricates等4.辅音清浊特征voicing辅音的送气特征aspiration5.元音vowel分类标准舌翘位置,舌高和嘴唇的形状6双元音diphthongs,有元音过渡vowel glides1. Articulatory phonetics mainly studies __.a. the physical properties of the sounds produced in speechb. the perception of soundsc. the combination of soundsd. the production of sounds2. The distinction between vowel s and consonants lies in __a. the place of articulationb.the obstruction f airstreamc. the position of the tongued. the shape of the lips3. What is the common factor of the three sounds: p, k ta. voicelessb. spreadc.voicedd.nasal4. What phonetic feature distinguish the p in please and the p in speak?a. voicingb. aspirationc.roundnessd. nasality5.Which of the following is not a distinctive feature in English?b.nasalc. approximationd. aspiration6.The phonological features of the consonant k are __a. voiced stopb. voiceless stopc. voiced fricatived. voiceless fricative7.p is divverent from k in __a. the manner of articulationb. the shape of the lipsc. the vibration of the vocal cordsd.the palce of articualtion8.Vibration of the vocal cords results in __a. aspirationb.nasalityc. obstructiond. voicing第三节音位学phonology1.音位学与语音学的区别:语音学着重于语音的自然属性,主要关注所有语言中人可能发出的所有声音;音位学则强调语音的社会功能,其对象是某一种语言中可以用来组合成词句的那些语音。

Advances in

Advances in

Advances in Geosciences,4,17–22,2005 SRef-ID:1680-7359/adgeo/2005-4-17 European Geosciences Union©2005Author(s).This work is licensed under a Creative CommonsLicense.Advances in GeosciencesIncorporating level set methods in Geographical Information Systems(GIS)for land-surface process modelingD.PullarGeography Planning and Architecture,The University of Queensland,Brisbane QLD4072,Australia Received:1August2004–Revised:1November2004–Accepted:15November2004–Published:9August2005nd-surface processes include a broad class of models that operate at a landscape scale.Current modelling approaches tend to be specialised towards one type of pro-cess,yet it is the interaction of processes that is increasing seen as important to obtain a more integrated approach to land management.This paper presents a technique and a tool that may be applied generically to landscape processes. The technique tracks moving interfaces across landscapes for processes such as waterflow,biochemical diffusion,and plant dispersal.Its theoretical development applies a La-grangian approach to motion over a Eulerian grid space by tracking quantities across a landscape as an evolving front. An algorithm for this technique,called level set method,is implemented in a geographical information system(GIS).It fits with afield data model in GIS and is implemented as operators in map algebra.The paper describes an implemen-tation of the level set methods in a map algebra program-ming language,called MapScript,and gives example pro-gram scripts for applications in ecology and hydrology.1IntroductionOver the past decade there has been an explosion in the ap-plication of models to solve environmental issues.Many of these models are specific to one physical process and of-ten require expert knowledge to use.Increasingly generic modeling frameworks are being sought to provide analyti-cal tools to examine and resolve complex environmental and natural resource problems.These systems consider a vari-ety of land condition characteristics,interactions and driv-ing physical processes.Variables accounted for include cli-mate,topography,soils,geology,land cover,vegetation and hydro-geography(Moore et al.,1993).Physical interactions include processes for climatology,hydrology,topographic landsurface/sub-surfacefluxes and biological/ecological sys-Correspondence to:D.Pullar(d.pullar@.au)tems(Sklar and Costanza,1991).Progress has been made in linking model-specific systems with tools used by environ-mental managers,for instance geographical information sys-tems(GIS).While this approach,commonly referred to as loose coupling,provides a practical solution it still does not improve the scientific foundation of these models nor their integration with other models and related systems,such as decision support systems(Argent,2003).The alternative ap-proach is for tightly coupled systems which build functional-ity into a system or interface to domain libraries from which a user may build custom solutions using a macro language or program scripts.The approach supports integrated models through interface specifications which articulate the funda-mental assumptions and simplifications within these models. The problem is that there are no environmental modelling systems which are widely used by engineers and scientists that offer this level of interoperability,and the more com-monly used GIS systems do not currently support space and time representations and operations suitable for modelling environmental processes(Burrough,1998)(Sui and Magio, 1999).Providing a generic environmental modeling framework for practical environmental issues is challenging.It does not exist now despite an overwhelming demand because there are deep technical challenges to build integrated modeling frameworks in a scientifically rigorous manner.It is this chal-lenge this research addresses.1.1Background for ApproachThe paper describes a generic environmental modeling lan-guage integrated with a Geographical Information System (GIS)which supports spatial-temporal operators to model physical interactions occurring in two ways.The trivial case where interactions are isolated to a location,and the more common and complex case where interactions propa-gate spatially across landscape surfaces.The programming language has a strong theoretical and algorithmic basis.The-oretically,it assumes a Eulerian representation of state space,Fig.1.Shows a)a propagating interface parameterised by differ-ential equations,b)interface fronts have variable intensity and may expand or contract based onfield gradients and driving process. but propagates quantities across landscapes using Lagrangian equations of motion.In physics,a Lagrangian view focuses on how a quantity(water volume or particle)moves through space,whereas an Eulerian view focuses on a localfixed area of space and accounts for quantities moving through it.The benefit of this approach is that an Eulerian perspective is em-inently suited to representing the variation of environmen-tal phenomena across space,but it is difficult to conceptu-alise solutions for the equations of motion and has compu-tational drawbacks(Press et al.,1992).On the other hand, the Lagrangian view is often not favoured because it requires a global solution that makes it difficult to account for local variations,but has the advantage of solving equations of mo-tion in an intuitive and numerically direct way.The research will address this dilemma by adopting a novel approach from the image processing discipline that uses a Lagrangian ap-proach over an Eulerian grid.The approach,called level set methods,provides an efficient algorithm for modeling a natural advancing front in a host of settings(Sethian,1999). The reason the method works well over other approaches is that the advancing front is described by equations of motion (Lagrangian view),but computationally the front propagates over a vectorfield(Eulerian view).Hence,we have a very generic way to describe the motion of quantities,but can ex-plicitly solve their advancing properties locally as propagat-ing zones.The research work will adapt this technique for modeling the motion of environmental variables across time and space.Specifically,it will add new data models and op-erators to a geographical information system(GIS)for envi-ronmental modeling.This is considered to be a significant research imperative in spatial information science and tech-nology(Goodchild,2001).The main focus of this paper is to evaluate if the level set method(Sethian,1999)can:–provide a theoretically and empirically supportable methodology for modeling a range of integral landscape processes,–provide an algorithmic solution that is not sensitive to process timing,is computationally stable and efficient as compared to conventional explicit solutions to diffu-sive processes models,–be developed as part of a generic modelling language in GIS to express integrated models for natural resource and environmental problems?The outline for the paper is as follow.The next section will describe the theory for spatial-temporal processing us-ing level sets.Section3describes how this is implemented in a map algebra programming language.Two application examples are given–an ecological and a hydrological ex-ample–to demonstrate the use of operators for computing reactive-diffusive interactions in landscapes.Section4sum-marises the contribution of this research.2Theory2.1IntroductionLevel set methods(Sethian,1999)have been applied in a large collection of applications including,physics,chemistry,fluid dynamics,combustion,material science,fabrication of microelectronics,and computer vision.Level set methods compute an advancing interface using an Eulerian grid and the Lagrangian equations of motion.They are similar to cost distance modeling used in GIS(Burroughs and McDonnell, 1998)in that they compute the spread of a variable across space,but the motion is based upon partial differential equa-tions related to the physical process.The advancement of the interface is computed through time along a spatial gradient, and it may expand or contract in its extent.See Fig.1.2.2TheoryThe advantage of the level set method is that it models mo-tion along a state-space gradient.Level set methods start with the equation of motion,i.e.an advancing front with velocity F is characterised by an arrival surface T(x,y).Note that F is a velocityfield in a spatial sense.If F was constant this would result in an expanding series of circular fronts,but for different values in a velocityfield the front will have a more contorted appearance as shown in Fig.1b.The motion of thisinterface is always normal to the interface boundary,and its progress is regulated by several factors:F=f(L,G,I)(1)where L=local properties that determine the shape of advanc-ing front,G=global properties related to governing forces for its motion,I=independent properties that regulate and influ-ence the motion.If the advancing front is modeled strictly in terms of the movement of entity particles,then a straightfor-ward velocity equation describes its motion:|∇T|F=1given T0=0(2) where the arrival function T(x,y)is a travel cost surface,and T0is the initial position of the interface.Instead we use level sets to describe the interface as a complex function.The level set functionφis an evolving front consistent with the under-lying viscosity solution defined by partial differential equa-tions.This is expressed by the equation:φt+F|∇φ|=0givenφ(x,y,t=0)(3)whereφt is a complex interface function over time period 0..n,i.e.φ(x,y,t)=t0..tn,∇φis the spatial and temporal derivatives for viscosity equations.The Eulerian view over a spatial domain imposes a discretisation of space,i.e.the raster grid,which records changes in value z.Hence,the level set function becomesφ(x,y,z,t)to describe an evolv-ing surface over time.Further details are given in Sethian (1999)along with efficient algorithms.The next section de-scribes the integration of the level set methods with GIS.3Map algebra modelling3.1Map algebraSpatial models are written in a map algebra programming language.Map algebra is a function-oriented language that operates on four implicit spatial data types:point,neighbour-hood,zonal and whole landscape surfaces.Surfaces are typ-ically represented as a discrete raster where a point is a cell, a neighbourhood is a kernel centred on a cell,and zones are groups of mon examples of raster data include ter-rain models,categorical land cover maps,and scalar temper-ature surfaces.Map algebra is used to program many types of landscape models ranging from land suitability models to mineral exploration in the geosciences(Burrough and Mc-Donnell,1998;Bonham-Carter,1994).The syntax for map algebra follows a mathematical style with statements expressed as equations.These equations use operators to manipulate spatial data types for point and neighbourhoods.Expressions that manipulate a raster sur-face may use a global operation or alternatively iterate over the cells in a raster.For instance the GRID map algebra (Gao et al.,1993)defines an iteration construct,called do-cell,to apply equations on a cell-by-cell basis.This is triv-ially performed on columns and rows in a clockwork manner. However,for environmental phenomena there aresituations Fig.2.Spatial processing orders for raster.where the order of computations has a special significance. For instance,processes that involve spreading or transport acting along environmental gradients within the landscape. Therefore special control needs to be exercised on the order of execution.Burrough(1998)describes two extra control mechanisms for diffusion and directed topology.Figure2 shows the three principle types of processing orders,and they are:–row scan order governed by the clockwork lattice struc-ture,–spread order governed by the spreading or scattering ofa material from a more concentrated region,–flow order governed by advection which is the transport of a material due to velocity.Our implementation of map algebra,called MapScript (Pullar,2001),includes a special iteration construct that sup-ports these processing orders.MapScript is a lightweight lan-guage for processing raster-based GIS data using map alge-bra.The language parser and engine are built as a software component to interoperate with the IDRISI GIS(Eastman, 1997).MapScript is built in C++with a class hierarchy based upon a value type.Variants for value types include numeri-cal,boolean,template,cells,or a grid.MapScript supports combinations of these data types within equations with basic arithmetic and relational comparison operators.Algebra op-erations on templates typically result in an aggregate value assigned to a cell(Pullar,2001);this is similar to the con-volution integral in image algebras(Ritter et al.,1990).The language supports iteration to execute a block of statements in three ways:a)docell construct to process raster in a row scan order,b)dospread construct to process raster in a spreadwhile(time<100)dospreadpop=pop+(diffuse(kernel*pop))pop=pop+(r*pop*dt*(1-(pop/K)) enddoendwhere the diffusive constant is stored in thekernel:Fig.3.Map algebra script and convolution kernel for population dispersion.The variable pop is a raster,r,K and D are constants, dt is the model time step,and the kernel is a3×3template.It is assumed a time step is defined and the script is run in a simulation. Thefirst line contained in the nested cell processing construct(i.e. dospread)is the diffusive term and the second line is the population growth term.order,c)doflow to process raster byflow order.Examples are given in subsequent sections.Process models will also involve a timing loop which may be handled as a general while(<condition>)..end construct in MapScript where the condition expression includes a system time variable.This time variable is used in a specific fashion along with a system time step by certain operators,namely diffuse()andfluxflow() described in the next section,to model diffusion and advec-tion as a time evolving front.The evolving front represents quantities such as vegetation growth or surface runoff.3.2Ecological exampleThis section presents an ecological example based upon plant dispersal in a landscape.The population of a species follows a controlled growth rate and at the same time spreads across landscapes.The theory of the rate of spread of an organism is given in Tilman and Kareiva(1997).The area occupied by a species grows log-linear with time.This may be modelled by coupling a spatial diffusion term with an exponential pop-ulation growth term;the combination produces the familiar reaction-diffusion model.A simple growth population model is used where the reac-tion term considers one population controlled by births and mortalities is:dN dt =r·N1−NK(4)where N is the size of the population,r is the rate of change of population given in terms of the difference between birth and mortality rates,and K is the carrying capacity.Further dis-cussion of population models can be found in Jrgensen and Bendoricchio(2001).The diffusive term spreads a quantity through space at a specified rate:dudt=Dd2udx2(5) where u is the quantity which in our case is population size, and D is the diffusive coefficient.The model is operated as a coupled computation.Over a discretized space,or raster,the diffusive term is estimated using a numerical scheme(Press et al.,1992).The distance over which diffusion takes place in time step dt is minimally constrained by the raster resolution.For a stable computa-tional process the following condition must be satisfied:2Ddtdx2≤1(6) This basically states that to account for the diffusive pro-cess,the term2D·dx is less than the velocity of the advancing front.This would not be difficult to compute if D is constant, but is problematic if D is variable with respect to landscape conditions.This problem may be overcome by progressing along a diffusive front over the discrete raster based upon distance rather than being constrained by the cell resolution.The pro-cessing and diffusive operator is implemented in a map al-gebra programming language.The code fragment in Fig.3 shows a map algebra script for a single time step for the cou-pled reactive-diffusion model for population growth.The operator of interest in the script shown in Fig.3is the diffuse operator.It is assumed that the script is run with a given time step.The operator uses a system time step which is computed to balance the effect of process errors with effi-cient computation.With knowledge of the time step the it-erative construct applies an appropriate distance propagation such that the condition in Eq.(3)is not violated.The level set algorithm(Sethian,1999)is used to do this in a stable and accurate way.As a diffusive front propagates through the raster,a cost distance kernel assigns the proper time to each raster cell.The time assigned to the cell corresponds to the minimal cost it takes to reach that cell.Hence cell pro-cessing is controlled by propagating the kernel outward at a speed adaptive to the local context rather than meeting an arbitrary global constraint.3.3Hydrological exampleThis section presents a hydrological example based upon sur-face dispersal of excess rainfall across the terrain.The move-ment of water is described by the continuity equation:∂h∂t=e t−∇·q t(7) where h is the water depth(m),e t is the rainfall excess(m/s), q is the discharge(m/hr)at time t.Discharge is assumed to have steady uniformflow conditions,and is determined by Manning’s equation:q t=v t h t=1nh5/3ts1/2(8)putation of current cell(x+ x,t,t+ ).where q t is theflow velocity(m/s),h t is water depth,and s is the surface slope(m/m).An explicit method of calcula-tion is used to compute velocity and depth over raster cells, and equations are solved at each time step.A conservative form of afinite difference method solves for q t in Eq.(5). To simplify discussions we describe quasi-one-dimensional equations for theflow problem.The actual numerical com-putations are normally performed on an Eulerian grid(Julien et al.,1995).Finite-element approximations are made to solve the above partial differential equations for the one-dimensional case offlow along a strip of unit width.This leads to a cou-pled model with one term to maintain the continuity offlow and another term to compute theflow.In addition,all calcu-lations must progress from an uphill cell to the down slope cell.This is implemented in map algebra by a iteration con-struct,called doflow,which processes a raster byflow order. Flow distance is measured in cell size x per unit length. One strip is processed during a time interval t(Fig.4).The conservative solution for the continuity term using afirst or-der approximation for Eq.(5)is derived as:h x+ x,t+ t=h x+ x,t−q x+ x,t−q x,txt(9)where the inflow q x,t and outflow q x+x,t are calculated in the second term using Equation6as:q x,t=v x,t·h t(10) The calculations approximate discharge from previous time interval.Discharge is dynamically determined within the continuity equation by water depth.The rate of change in state variables for Equation6needs to satisfy a stability condition where v· t/ x≤1to maintain numerical stabil-ity.The physical interpretation of this is that afinite volume of water wouldflow across and out of a cell within the time step t.Typically the cell resolution isfixed for the raster, and adjusting the time step requires restarting the simulation while(time<120)doflow(dem)fvel=1/n*pow(depth,m)*sqrt(grade)depth=depth+(depth*fluxflow(fvel)) enddoendFig.5.Map algebra script for excess rainfallflow computed over a 120minute event.The variables depth and grade are rasters,fvel is theflow velocity,n and m are constants in Manning’s equation.It is assumed a time step is defined and the script is run in a simulation. Thefirst line in the nested cell processing(i.e.doflow)computes theflow velocity and the second line computes the change in depth from the previous value plus any net change(inflow–outflow)due to velocityflux across the cell.cycle.Flow velocities change dramatically over the course of a storm event,and it is problematic to set an appropriate time step which is efficient and yields a stable result.The hydrological model has been implemented in a map algebra programming language Pullar(2003).To overcome the problem mentioned above we have added high level oper-ators to compute theflow as an advancing front over a land-scape.The time step advances this front adaptively across the landscape based upon theflow velocity.The level set algorithm(Sethian,1999)is used to do this in a stable and accurate way.The map algebra script is given in Fig.5.The important operator is thefluxflow operator.It computes the advancing front for waterflow across a DEM by hydrologi-cal principles,and computes the local drainageflux rate for each cell.Theflux rate is used to compute the net change in a cell in terms offlow depth over an adaptive time step.4ConclusionsThe paper has described an approach to extend the function-ality of tightly coupled environmental models in GIS(Ar-gent,2004).A long standing criticism of GIS has been its in-ability to handle dynamic spatial models.Other researchers have also addressed this issue(Burrough,1998).The con-tribution of this paper is to describe how level set methods are:i)an appropriate scientific basis,and ii)able to perform stable time-space computations for modelling landscape pro-cesses.The level set method provides the following benefits:–it more directly models motion of spatial phenomena and may handle both expanding and contracting inter-faces,–is based upon differential equations related to the spatial dynamics of physical processes.Despite the potential for using level set methods in GIS and land-surface process modeling,there are no commercial or research systems that use this mercial sys-tems such as GRID(Gao et al.,1993),and research systems such as PCRaster(Wesseling et al.,1996)offerflexible andpowerful map algebra programming languages.But opera-tions that involve reaction-diffusive processing are specific to one context,such as groundwaterflow.We believe the level set method offers a more generic approach that allows a user to programflow and diffusive landscape processes for a variety of application contexts.We have shown that it pro-vides an appropriate theoretical underpinning and may be ef-ficiently implemented in a GIS.We have demonstrated its application for two landscape processes–albeit relatively simple examples–but these may be extended to deal with more complex and dynamic circumstances.The validation for improved environmental modeling tools ultimately rests in their uptake and usage by scientists and engineers.The tool may be accessed from the web site .au/projects/mapscript/(version with enhancements available April2005)for use with IDRSIS GIS(Eastman,1997)and in the future with ArcGIS. It is hoped that a larger community of users will make use of the methodology and implementation for a variety of environmental modeling applications.Edited by:P.Krause,S.Kralisch,and W.Fl¨u gelReviewed by:anonymous refereesReferencesArgent,R.:An Overview of Model Integration for Environmental Applications,Environmental Modelling and Software,19,219–234,2004.Bonham-Carter,G.F.:Geographic Information Systems for Geo-scientists,Elsevier Science Inc.,New York,1994. Burrough,P.A.:Dynamic Modelling and Geocomputation,in: Geocomputation:A Primer,edited by:Longley,P.A.,et al., Wiley,England,165-191,1998.Burrough,P.A.and McDonnell,R.:Principles of Geographic In-formation Systems,Oxford University Press,New York,1998. Gao,P.,Zhan,C.,and Menon,S.:An Overview of Cell-Based Mod-eling with GIS,in:Environmental Modeling with GIS,edited by: Goodchild,M.F.,et al.,Oxford University Press,325–331,1993.Goodchild,M.:A Geographer Looks at Spatial Information Theory, in:COSIT–Spatial Information Theory,edited by:Goos,G., Hertmanis,J.,and van Leeuwen,J.,LNCS2205,1–13,2001.Jørgensen,S.and Bendoricchio,G.:Fundamentals of Ecological Modelling,Elsevier,New York,2001.Julien,P.Y.,Saghafian,B.,and Ogden,F.:Raster-Based Hydro-logic Modelling of Spatially-Varied Surface Runoff,Water Re-sources Bulletin,31(3),523–536,1995.Moore,I.D.,Turner,A.,Wilson,J.,Jenson,S.,and Band,L.:GIS and Land-Surface-Subsurface Process Modeling,in:Environ-mental Modeling with GIS,edited by:Goodchild,M.F.,et al., Oxford University Press,New York,1993.Press,W.,Flannery,B.,Teukolsky,S.,and Vetterling,W.:Numeri-cal Recipes in C:The Art of Scientific Computing,2nd Ed.Cam-bridge University Press,Cambridge,1992.Pullar,D.:MapScript:A Map Algebra Programming Language Incorporating Neighborhood Analysis,GeoInformatica,5(2), 145–163,2001.Pullar,D.:Simulation Modelling Applied To Runoff Modelling Us-ing MapScript,Transactions in GIS,7(2),267–283,2003. Ritter,G.,Wilson,J.,and Davidson,J.:Image Algebra:An Overview,Computer Vision,Graphics,and Image Processing, 4,297–331,1990.Sethian,J.A.:Level Set Methods and Fast Marching Methods, Cambridge University Press,Cambridge,1999.Sklar,F.H.and Costanza,R.:The Development of Dynamic Spa-tial Models for Landscape Ecology:A Review and Progress,in: Quantitative Methods in Ecology,Springer-Verlag,New York, 239–288,1991.Sui,D.and R.Maggio:Integrating GIS with Hydrological Mod-eling:Practices,Problems,and Prospects,Computers,Environ-ment and Urban Systems,23(1),33–51,1999.Tilman,D.and P.Kareiva:Spatial Ecology:The Role of Space in Population Dynamics and Interspecific Interactions.Princeton University Press,Princeton,New Jersey,USA,1997. Wesseling C.G.,Karssenberg, D.,Burrough,P. A.,and van Deursen,W.P.:Integrating Dynamic Environmental Models in GIS:The Development of a Dynamic Modelling Language, Transactions in GIS,1(1),40–48,1996.。

英语作文随机生成方法

英语作文随机生成方法

英语作文随机生成方法Title: Methods of Random English Essay Generation。

In today's digital age, the generation of random English essays has become a fascinating subject, intertwining creativity and technology. With the proliferation of artificial intelligence and natural language processing, various methods have emerged to automatically generate essays on diverse topics. This essay delves into the most prevalent techniques used for random English essay generation, drawing insights from the most downloaded samples online.1. Markov Chain Text Generation:Markov chain text generation is a statistical method that models the probability of transitioning from one word to another based on a given corpus. By analyzing a large dataset of English text, a Markov chain algorithm can generate coherent sentences by predicting the next wordbased on the previous one. This method has gainedpopularity due to its simplicity and effectiveness in mimicking human language patterns.2. Recurrent Neural Networks (RNNs):Recurrent Neural Networks, particularly Long Short-Term Memory (LSTM) networks, have revolutionized the fieldof natural language generation. RNNs process sequences of words and learn to generate text character by character or word by word. By training on a vast amount of English text, RNNs can capture intricate patterns and nuances of language, producing essays that resemble human writing. The generated essays often exhibit impressive coherence and readability.3. GPT (Generative Pre-trained Transformer) Models:GPT models, such as GPT-3, represent the pinnacle of natural language generation technology. Pre-trained on massive datasets, these models have a profoundunderstanding of various linguistic structures and can generate high-quality essays on almost any topic. Byemploying a transformer architecture, GPT models excel at capturing long-range dependencies in text, resulting in essays that are not only coherent but also contextually relevant and insightful.4. Template-Based Generation:Template-based generation involves filling in predefined templates with randomly selected words or phrases. While less sophisticated than neural network-based approaches, this method is straightforward and can produce essays with a predictable structure. By employing templates for introductions, body paragraphs, and conclusions, this method ensures that the generated essays adhere to conventional essay formats.5. Hybrid Approaches:Some advanced techniques combine multiple methods to leverage their respective strengths. For instance, a hybrid approach might use a GPT model to generate the overall structure and main ideas of an essay, while employing atemplate-based system to fill in specific details and examples. By integrating diverse techniques, hybrid approaches aim to achieve a balance between creativity and control in essay generation.6. Evaluation and Fine-Tuning:Regardless of the method used, evaluating thequality of generated essays is crucial. Metrics such as coherence, grammaticality, and relevance to the given topic are commonly used to assess the performance of essay generation systems. Additionally, fine-tuning the models based on feedback from human evaluators can further enhance the quality of generated essays, making them indistinguishable from human-written ones.In conclusion, the generation of random English essays encompasses a variety of sophisticated techniques, ranging from statistical models like Markov chains to state-of-the-art neural network architectures like GPT. These methods leverage vast amounts of data and powerful computational resources to produce essays that are increasinglyindistinguishable from those written by humans. As technology continues to advance, the boundaries of automated essay generation will continue to be pushed, offering new possibilities for creative expression and linguistic exploration.。

【密训】00830 现代语言学

【密训】00830 现代语言学

现代语言学(课程代码:00830)Chapter1:Introduction1.Define the following terms:1).Linguistics:It is generally defined as the scientific study of language.2).General linguistics(普通语言学):The study of language as a whole is called general linguistics.3).Applied linguistics(应用语言学):In a narrow sense,applied linguistics refers to the application of linguistic principles and theories to language teaching and learning,especially the teaching of foreign and second languages.In a broad sense,it refers to the application of linguistic findings to the solution of practical problems such as the recovery of speech ability.4).Synchronic study(共时性研究):The study of a language at some point in time.e.g.A study of the features of the English used in Shakespeare's time is a synchronic study.5).Diachronic study(历时性研究):The study of a language as it changes through time.A diachronic study of language is a historical study,which studies the historical development of language over a period of time.e.g.a study of the changes English has undergone since Shakespeare's time is a diachronic study. 6).Language competence(语言能力):The ideal user's knowledge of the rules of his language.A transformational-generative grammar(转化生成语法)is a model of language competence.7).Language performance(语言行为):performance is the actual realization of the ideal language user's knowledge of the rules in linguistic communication. 8).Langue(语言):Langue refers to the abstract linguistic system shared by all the members of a speech community;Langue is the set of conventions and rules which language users all have to follow;Langue is relatively stable,it does not change frequently.9).Parole(言语):Parole refers to the realization of langue in actual use;parole is the concrete use of the conventions and the application of the rules;parole varies from person to person,and from situation to situation.10).Language(语言):Language is a system of arbitrary vocal symbols used for human communication.11).Arbitrariness(任意性):It is one of the design features of language.It means that there is no logical connection between meanings and sounds.A good example is the fact that different sounds are used to refer to the same object in different languages.12).Productivity(多产性):Language is productive or creative in that it makes possible the construction and interpretation of new signals by its users.13).Duality(二元性):Language is a system,which consists of two sets of structure,or two levels,one of sounds at the lower or basic level,and the other of meanings at the higher level.14).Displacement(移位性):language can be used to refer to things which are present or not present,real or imagined matters in the past,present,or future,or in far-away places.In other words,language can be used to refer to contexts removed from the immediate situations of the speaker.15).Cultural transmission(文化传递性):While we are born with the ability to acquire language,the details of any language are not genetically transmitted,but instead have to be taught and learned.16).Design features(普遍特征):It refers to the defining properties of human language that distinguish it from any animal system of communication2.Explain the following definition of linguistics:Linguistics is the scientific study of language.Linguistics investigates not any particular language,but languages in general. Linguistic study is scientific because it is based on the systematic investigation of authentic(可靠的,真实的)language data.No serious linguistic conclusion is reached until after the linguist has done the following three things:observing the way language is actually used,formulating some hypotheses,and testing these hypotheses against linguistic facts to prove their validity.3.What are the branches of linguistics?What does each of them study?(语言学的主要分支是什么。

  1. 1、下载文档前请自行甄别文档内容的完整性,平台不提供额外的编辑、内容补充、找答案等附加服务。
  2. 2、"仅部分预览"的文档,不可在线预览部分如存在完整性等问题,可反馈申请退款(可完整预览的文档不适用该条件!)。
  3. 3、如文档侵犯您的权益,请联系客服反馈,我们会尽快为您处理(人工客服工作时间:9:00-18:30)。

GraSp: Grammar learning from unlabelled speech corporaPeter Juel HenrichsenCMOLCenter for Computational Modelling of Language c/o Dept. of Computational LinguisticsCopenhagen Business SchoolFrederiksberg, Denmarkpjuel@id.cbs.dkAbstractThis paper presents the ongoing projectComputational Models of First LanguageAcquisition, together with its currentproduct, the learning algorithm GraSp.GraSp is designed specifically forinducing grammars from large, unlabelledcorpora of spontaneous (i.e. unscripted)speech. The learning algorithm does notassume a predefined grammaticaltaxonomy; rather the determination ofcategories and their relations is consideredas part of the learning task. While GraSplearning can be used for a range ofpractical tasks, the long-term goal of theproject is to contribute to the debate ofinnate linguistic knowledge – under thehypothesis that there is no such.IntroductionMost current models of grammar learning assume a set of primitive linguistic categories and constraints, the learning process being modelled as category filling and rule instantiation – rather than category formation and rule creation. Arguably, distributing linguistic data over predefined categories and templates does not qualify as grammar 'learning' in the strictest sense, but is better described as 'adjustment' or 'adaptation'. Indeed, Chomsky, the prime advocate of the hypothesis of innate linguistic principles, has claimed that "in certain fundamental respects we do not really learn language" (Chomsky 1980: 134). As Chomsky points out, the complexity of the learning task is greatly reduced given a structure of primitive linguistic constraints ("a highly restrictive schematism", ibid.). It has however been very hard to establish independently the psychological reality of such a structure, and the question of innateness is still far from settled.While a decisive experiment may never be conceived, the issue could be addressed indirectly, e.g. by asking: Are innate principles and parameters necessary preconditions for grammar acquisition? Or rephrased in the spirit of constructive logic: Can a learning algorithm be devised that learns what the infant learns without incorporating specific linguistic axioms? The presentation of such an algorithm would certainly undermine arguments referring to the 'poverty of the stimulus', showing the innateness hypothesis to be dispensable.This paper presents our first try.1The essential algorithm1.1Psycho-linguistic preconditions Typical spontaneous speech is anything but syntactically 'well-formed' in the Chomskyan sense of the word.right well let's er --= let's look at the applications - erm - let me just ask initially this -- I discussed it with er Reith er but we'll = have to go into it a bit further - is it is it within our erm er = are we free er to er draw up a rather = exiguous list - of people to interview(sample from the London-Lund corpus) Yet informal speech is not perceived as being disorderly (certainly not by the language learning infant), suggesting that its organizingprinciples differ from those of the written language. So, arguably, a speech grammar inducing algorithm should avoid referring to the usual categories of text based linguistics –'sentence', 'determiner phrase', etc.1Instead we allow a large, indefinite number of (indistinguishable) basic categories – and then leave it to the learner to shape them, fill them up, and combine them. For this task, the learner needs a built-in concept of constituency. This kind of innateness is not in conflict with our main hypothesis, we believe, since constituency as such is not specific to linguistic structure.1.2Logical preliminariesFor the reasons explained, we want the learning algorithm to be strictly data-driven. This puts special demands on our parser which must be robust enough to accept input strings with little or no hints of syntactic structure (for the early stages of a learning session), while at the same time retaining the discriminating powers of a standard context free parser (for the later stages).Our solution is a sequent calculus, a variant of the Gentzen-Lambek categorial grammar formalism (L ) enhanced with non-classical rules for isolating a residue of uninterpretable sequent elements. The classical part is identical to L (except that antecedents may be empty).1 Hoekstra (2000) and Nivre (2001) discuss theannotation of spoken corpora with traditional tags.These seven rules capture the input parts that can be interpreted as syntactic constituents (examples below). For the remaining parts, we include two non-classical rules (σL and σR ).2By way of an example, consider the input stringright well let's er let's look at the applicationsas analyzed in an early stage of a learning session. Since no lexical structure has developed yet, the input is mapped onto a sequent of basic (dummy) categories:3c 29 c 22 c 81 c 5 c 81 c 215 c 10 c 1 c 891 ⇒ c 0Using σL recursively, each category of the antecedent (the part to the left of ⇒) is removed from the main sequent. As the procedure is fairly simple, we just show a fragment of the proof.Notice that proofs read most easily bottom-up.c 0–––––– σR c 81+ c 10+ c 1+ c 891+⇒ c 0–––––––––––––––––––––––– σL...–––––––––––––––––––– σLc 215+c 81 c 10 c 1 c 891 ⇒ c 0––––––––––––––––––––––––– σL c 5+c 81 c 215 c 10 c 1 c 891 ⇒ c 0––––––––––––––––––––––––––––––– σL ... c 5 c 81 c 215 c 10 c 1 c 891 ⇒ c 0In this proof there are no link s, meaning that no grammatical structure was found. Later, when the lexicon has developed, the parser may2 The calculus presented here is slightly simplified.Two rules are missing, and so is the reserved category T ('noise') used e.g. for consequents (in place of c 0 of the example). Cf. Henrichsen (2000).3 By convention the indexing of category names reflects the frequency distribution: If word W has rank n in the training corpus, it is initialized as W :c n .recognize more structure in the same input:–––––––l––––––––lc10⇒c10c891⇒c891–––––––––––––––––*Rc10 c891⇒ c10*c891c81 c215⇒ c0––––––l–––––––––––––––––––––––––––––/L c1⇒ c1c81 c215/(c10*c891) c10 c891⇒ c0–––––––––––––––––––––––––––––––––––––\L ... c81c215/(c10*c891)c10 c1c1\c891⇒ c0 ... let's look at the applicationsThis proof tree has three link s, meaning that the disorder of the input string (wrt. the new lexicon) has dropped by three degrees. More on disorder shortly.1.3The algorithm in outlineHaving presented the sequent parser, we now show its embedding in the learning algorithm GraSp (Gra mmar of Sp eech).For reasons mentioned earlier, the common inventory of categories (S, NP, CN, etc) is avoided. Instead each lexeme initially inhabits its own proto-category. If a training corpus has, say, 12,345 word types the initial lexicon maps them onto as many different categories. A learning session, then, is a sequence of lexical changes, introducing, removing, and manipulating the operators /, \, and * as guided by a well-defined measure of structural disorder.We prefer formal terms without a linguistic bias ("no innate linguistic constraints"). Suggestive linguistic interpretations are provided in square brackets.A-F summarize the learning algorithm.A) There are categories. Complex categories are built from basic categories using /, \, and *: Basic categoriesc1, c2, c3, ... , c12345 , ...Complex categoriesc1\c12345, c2/c3, c4*c5, c2/(c3\(c4*c5))B) A lexicon is a mapping of lexemes [word types represented in phonetic or enriched-orthographic encoding] onto categories.C) An input segment is an instance of a lexeme [an input word]. A solo is a string of segments [an utterance delimited by e.g. turntakes and pauses]. A corpus is a bag of soli [a transcript of a conversation].D) Applying an update L:C1→C2 in lexicon Lex means changing the mapping of L in Lex from C1 to C2. Valid changes are minimal, i.e. C2 is construed from C1 by adding or removing 1 basic category (using \, /, or *).E) The learning process is guided by a measure of disorder. The disorder function Dis takes a sequent Σ [the lexical mapping of an utterance] returning the number of uninterpretable atoms in Σ, i.e. σ+s and σ–s in a (maximally linked) proof. Dis(Σ)=0 iff Σ is Lambek valid. Examples: Dis( c a/c b c b⇒ c a )= 0Dis( c a/c b c b⇒ c c )= 2Dis( c b c a/c b⇒ c c )= 4Dis( c a/c b c c c b ⇒ c a )= 1Dis( c a/c c c b c a\c c ⇒ c a )= 2DIS(Lex,K) is the total amount of disorder in training corpus K wrt. lexicon Lex, i.e. the sum of Dis-values for all soli in K as mapped by Lex.F) A learning session is an iterative process. In each iteration i a suitable update U i is applied in the lexicon Lex i–1 producing Lex i . Quantifying over all possible updates, U i is picked so as to maximize the drop in disorder (DisDrop):DisDrop = DIS(Lex i–1,K) – DIS(Lex i,K)The session terminates when no suitable update remains.It is possible to GraSp efficiently and yet preserve logical completeness. See Henrichsen (2000) for discussion and demonstrations.1.4A staged learning sessionGiven this tiny corpus of four soli ('utterances')if you must you canif you must you must and if we must we mustif you must you can and if you can you mustif we must you must and if you must you must, GraSp produces the lexicon below.As shown, training corpora can be manufactured so as to produce lexical structure fairly similar to what is found in CG textbooks. Such close similarity is however not typical of 'naturalistic' learning sessions – as will be clear in section 2.1.5 Why categorial grammar?In CG, all structural information is located in the lexicon. Grammar rules (e.g. VP→V t N) and parts of speech (e.g. 'transitive verb', 'common noun') are treated as variants of the same formal kind. This reduces the dimensionality of thelogical learning space, since a CG-based learner needs to induce just a single kind of structure.Besides its formal elegance, the CG basis accomodates a particular kind of cognitive models, viz. those that reject the idea of separate mental modules for lexical and grammatical processing (e.g. Bates 1997). As we see it, our formal approach allows us the luxury of not taking sides in the heated debate of modularity.5 2Learning from spoken languageThe current GraSp implementation completes a learning session in about one hour when fed with our main corpus.6 Such a session spans 2500-4000 iterations and delivers a lexicon rich 4 For perspicuity, two of the GraSped categories –viz. 'can':(c2\c5)*(c5\c1) and 'we':(c2/c6)*c6 – are replaced in the table by functional equivalents.5 A caveat: Even if we do share some tools with other CG-based NL learning programmes, our goals are distinct, and our results do not compare easily with e.g. Kanazawa (1994), Watkinson (2000). In terms of philosophy, GraSp seems closer to connectionist approaches to NLL.6 The Danish corpus BySoc (person interviews). Size: 1.0 mio. words. Duration: 100 hours. Style: Labovian interviews. Transcription: Enriched orthography. Tagging: none. Ref.: http://www.cphling.dk/BySoc in microparadigms and microstructure. Lexical structure develops mainly around content words while most function words retain their initial category. The structure grown is almost fractal in character with lots of inter-connected categories, while the traditional large open classes − nouns, verbs, prepositions, etc. − are absent as such. The following sections present some samples from the main corpus session (Henrichsen 2000 has a detailed description). 2.1Microparadigms{ "Den Franske", "Nyboder","Sølvgades", "Krebses" } These four lexemes – or rather lexeme clusters –chose to co-categorize. The collection does not resemble a traditional syntactic paradigm, yet the connection is quite clear: all four items appeared in the training corpus as names of primary schools.The final categories are superficially different, but are easily seen to be functionally equivalent.The same session delivered several other microparadigms: a collection of family members (in English translation: brother, grandfather, younger-brother, stepfather, sister-in-law, etc.), a class of negative polarity items, a class of mass terms, a class of disjunctive operators, etc. (Henrichsen 2000 6.4.2).GraSp-paradigms are usually small and almost always intuitively 'natural' (not unlike the small categories of L1 learners reported by e.g. Lucariello 1985).2.2MicrogrammarsGraSp'ed grammar rules are generally not of the kind studied within traditional phrase structure grammar. Still PSG-like 'islands' do occur, in the form of isolated networks of connected lexemes.Centred around lexeme 'Pauls', a microgrammar (of street names) has evolved almost directly translatable into rewrite rules:7PP → 'i' N 1 'Gade'PP → 'på' N 1 'Plads'PP → 'på' N 2N 1→ X 'Pauls'N 2→ X 'Annæ'N x → X YX → 'Sankt' | 'Skt.' | 'Sct.'Y→ 'Pauls' | 'Josef' | 'Joseph' | 'Knuds' | ...2.3Idioms and locutionsConsider the five utterances of the main corpus containing the word 'rafle' (cast-dice INF ):8det gør den der er ikke noget at rafle om der der er ikke så meget at rafle om der er ikke noget og rafle omsætte sig ned og rafle lidt med fyrene der at rafle om derOn most of its occurrences, 'rafle' takes part in the idiom "der er ikke noget/meget og/at rafle om", often followed by a resumptive 'der'(literally: there is not anything /much and /to7 Lexemes 'Sankt', 'Sct.', and 'Skt.' have in effectcocategorized, since it holds that (x /y )*y ⇒ x . This cocategorization is quite neat considering that GraSp is blind to the interior of lexemes. c 9 and c 22 are the categories of 'i' (in ) and 'på' (on ).8 In writing, only two out of five would probably qualify as syntactically well-formed sentences.cast-dice INF about (there ), meaning: this is not a subject of negotiations). Lexeme 'ikke' (category c 8) occurs in the left context of 'rafle' more often than not, and this fact is reflected in the final category of 'rafle':rafle: ((c 12\(c 8\(c 5\(c 7\c 5808))))/c 7)/c 42Similarly for the lexemes 'der' (c 7), 'er' (c 5), 'at'(c 12), and 'om' (c 42) which are also present in the argument structure of the category, while the top functor is the initial 'rafle' category (c 5808).The minimal context motivating the full rafle category is:("..." means that any amount and kind of material may intervene). This template is a quite accurate description of an acknowledged Danish idiom.Such idioms have a specific categorial signature in the GraSped lexicon: a rich, but flat argument structure (i.e. analyzed solely by σR )centered around a single low-frequency functor (analyzed by σL ). Further examples with the same signature:... i ...– all well-known Danish locutions.9There are of course plenty of simpler and faster algorithms available for extracting idioms.Most such algorithms however include specific knowledge about idioms (topological and morphological patterns, concepts of mutual information, heuristic and statistical rules, etc.).Our algorithm has no such inclination: it does not search for idioms, but merely finds them.Observe also that GraSp may induce idiom templates like the ones shown even from corpora without a single verbatim occurrence.9 For entry rafle , Danish-Danish dictionary Politikenhas this paradigmatic example: "Der er ikke noget at rafle om". Also fortænke , blæse , kinamands have examples near-identical with the learned templates.3Learning from exotic corporaIn order to test GraSp as a general purpose learner we have used the algorithm on a range of non-verbal data. We have had GraSp study melodic patterns in musical scores and prosodic patterns in spontaneous speech (and even dna-structure of the banana fly). Results are not yet conclusive, but encouraging (Henrichsen 2002).When fed with HTML-formatted text, GraSp delivers a lexical patchwork of linguistic structure and HTML-structure. GraSp's uncritical appetite for context-free structure makes it a candidate for intelligent web-crawling. We are preparing an experiment with a large number of cloned learners to be let loose in the internet, reporting back on the structure of the documents they see. Since GraSp produces formatting definitions as output (rather than requiring it as input), the algorithm could save the www-programmer the troubles of preparing his web-crawler for this-and-that format.Of course such experiments are side-issues. However, as discussed in the next section, learning from non-verbal sources may serve as an inspiration in the L1 learning domain also.4Towards a model of L1 acquisition4.1Artificial language learningTraining infants in language tasks within artificial (i.e. semantically empty) languages is an established psycho-linguistic method. Infants have been shown able to extract structural information – e.g. rules of phonemic segmentation, prosodic contour, and even abstract grammar (Cutler 1994, Gomez 1999, Ellefson 2000) – from streams of carefully designed nonsense. Such results are an important source of inspiration for us, since the experimental conditions are relatively easy to simulate. We are conducting a series of 'retakes' with the GraSp learner in the subject's role. Below we present an example.In an often-quoted experiment, psychologist Jenny Saffran and her team had eight-months-old infants listening to continuous streams of nonsense syllables: ti, do, pa, bu, la, go, etc. Some streams were organized in three-syllable 'words' like padoti and golabu (repeated in random order) while others consisted of the same syllables in random order. After just two minutes of listening, the subjects were able to distinguish the two kinds of streams. Conclusion: Infants can learn to identify compound words on the basis of structural clues alone, in a semantic vacuum.Presented with similar streams of syllables, the GraSp learner too discovers word-hood.It may be objected that such streams of presegmented syllables do not represent the experimental conditions faithfully, leaping over the difficult task of segmentation. While we do not yet have a definitive answer to this objection, we observe that replacing "pa do ti go la bu (..)" by "p a d o t i g o l a b u (..)" has the GraSp learner discover syllable-hood and word-hood on a par.114.2Naturalistic language learningEven if human learners can demonstrably learn structural rules without access to semantic and pragmatic cues, this is certainly not the typical L1 acquisition scenario. Our current learning model fails to reflect the natural conditions in a number of ways, being a purely syntactic calculus working on symbolic input organized in well-delimited strings. Natural learning, in contrast, draws on far richer input sources:•continuous (unsegmented) input streams •suprasegmental (prosodic) information•sensory data•background knowledge10 As seen, padoti has selected do for its functional head, and golabu, bu. These choices are arbitrary.11 The very influential Eimas (1971) showed one-month-old infants to be able to distinguish /p/ and /b/. Many follow-ups have established that phonemic segmentation develops very early and may be innate.Any model of first language acquisition must be prepared to integrate such information sources. Among these, the extra-linguistic sources are perhaps the most challenging, since they introduce a syntactic-semantic interface in the model. As it seems, the formal simplicity of one-dimensional learning (cf. sect. 1.5) is at stake.If, however, semantic information (such as sensory data) could be 'syntactified' and included in the lexical structure in a principled way, single stratum learning could be regained. We are currently working on a formal upgrading of the calculus using a framework of constructive type theory (Coquant 1988, Ranta 1994). In CTT, the radical lexicalism of categorial grammar is taken even a step further, representing semantic information in the same data structure as grammatical and lexical information. This formal upgrading takes a substantial refinement of the Dis function (cf. sect. 1.3 E) as the determination of 'structural disorder' must now include contextual reasoning (cf. Henrichsen 1998). We are pursuing a design with σ+ and σ– as instructions to respectively insert and search for information in a CTT-style context.These formal considerations are reflections of our cognitive hypotheses. Our aim is to study learning as a radically data-driven process drawing on linguistic and extra-linguistic information sources on a par – and we should like our formal system to fit like a glove.5Concluding remarksAs far as we know, GraSp is the first published algorithm for extracting grammatical taxonomy out of untagged corpora of spoken language.12 This in an uneasy situation, since if our findings are not comparable to those of other approaches to grammar learning, how could our results be judged − or falsified? Important issues wide open to discussion are: validation of results, psycho-linguistic relevance of the experimental setup, principled ways of surpassing the context-free limitations of Lambek grammar (inherited in GraSp), just to mention a few.On the other hand, already the spin-offs of our project (the collection of non-linguistic learners) do inspire confidence in our tenets, we 12 The learning experiment sketched in Moortgat (2001) shares some of GraSp's features.think – even if the big issue of psychological realism has so far only just been touched.The GraSp implementation referred to in this paper is available for test runs athttp://www.id.cbs.dk/~pjuel/GraSpReferencesBates, E.; J.C. Goodman (1997) On the Inseparability of Grammar and the Lexicon: Evidence From Acquisition, Aphasia, and Real-time Processing; Language and Cognitive Processes 12, 507-584 Chomsky, N. (1980) Rules and Representations; Columbia Univ. PressCoquant, T.; G. Huet (1988) The Calculus of Constructions; Info. & Computation 76, 95-120 Cutler, A. (1994) Segmentation Problems, Rhythmic Solutions; Lingua 92, 81-104Eimas, P.D.; E.D. Siqueland; P.W. Jusczyk (1971) Speech Perception in Infants; Science 171 303-306 Ellefson, M.R.; M.H.Christiansen (2000) Subjacency Constraints Without Universal Grammar: Evidence from Artificial Language Learning and Connectionist Modelling;22nd Ann. Conference of the Cognitive Science Society, Erlbaum, 645-650 Gomez, R.L.; L.A. Gerken (1999) Artificial Gram-mar Learning by 1-year-olds Leads to Specific and Abstract Knowledge; Cognition 70 109-135 Henrichsen, P.J. (1998) Does the Sentence Exist? Do We Need It?; in K. Korta et al. (eds) Discourse, Interaction, and Communication; Kluwer Acad. Henrichsen, P.J. (2000) Learning Within Grasp −Interactive Investigations into the Grammar of Speech; Ph.D., http://www.id.cbs.dk/~pjuel/GraSp Henrichsen, P.J. (2002) GraSp: Grammar Learning With a Healthy Appetite (in prep.)Hoekstra, H. et al. (2000) Syntactic Annotation for the Spoken Dutch Corpus Project; CLIN2000 Kanazawa (1994) Learnable Classes of CG; Ph.D. Moortgat, M. (2001) Structural Equations in Language Learning; 4th LACL2001 1-16Nivre, J.; L. Grönqvist (2001) Tagging a Corpus of Spoken Swedish: Int. Jn. of Corpus Ling. 6:1 47-78 Ranta, A. (1994) Type-Theoretical Grammar; Oxford Saffran, J.R. et al. (1996) Statistical Learning By 8-Months-Old Infants; Science 274 1926-1928 Watkinson S.; S. Manandhar (2000) Unsupervised Lexical Learning with CG; in Cussens J. et al. (eds) Learning Language in Logic; Springer。

相关文档
最新文档