牛津计算语言学手册

章节摘录

　　If morphophonological processes in a language are few and local the lemma lexi-con approach can still be successful. In our example it suffices to assume two pluralendings: -s and -es. For all base forms it must be specified whether the former or thelatter of the two endings may be attached.A part from the obvious limitations with regard to the treatment of morphopho-nological rules on a more general scale the approach has some other inherent restric-tions:The algorithm is geared towards analysis. For generation purposes, one needs acompletely different algorithm and data.Interpretation algorithms are language specific because they encode both thebasic concatenation algorithm and the specific exception-handling mechanism.The approach was developed for morphosyntactic analysis. An extension tohandle more generally the segmenting of word forms into morphs is difficult toachieve.

前言

　　Computational Linguistics is an interdisciplinary field concerned with the process-ing of language by computers. Since machine translation began to emerge somefifty years ago （see Martin Kays introduction below）， Computational Linguisticshas grown and developed exponentially. It has expanded theoretically through thedevelopment of computational and formal models of language. In the process it hasvastly increased the range and usefulness of its applications. At a time of continuingand vigorous growth the Oxford Handbook of Computational Linguistics providesa much-needed reference and guide. It aims to be of use to everyone interested inthe subject， including students wanting to familiarize themselves with its key areas，researchers in other areas in search of an appropriate model or method， and thosealreadyworking in the field who want to discover the latest developments in areasadjacent to their own.　　The Handbook is structured in three parts which reflect a natural progression fromtheory to applications.　　Part I introduces the fundamentals： it considers， from a computational perspective，the main areas of linguistics such as phonology， morphology， lexicography， syntax，semantics， discourse， pragmatics， and dialogue. It also looks at central issues in math-ematical linguistics such as formal grammars and languages， and complexity.　　Part II is devoted to the basic stages， tasks， methods， and resources in and requiredfor automatic language processing. It examines text segmentation， part-of-speechtagging， parsing， word-sense disambiguation， anaphora resolution， natural languagegeneration， speech recognition， text-to-speech synthesis， finite state technology，statistical methods， machine learning， lexical knowledge acquisition， evaluation， sub-languages， controlled languages， corpora， ontologies， and tree-adjoining grammars.　　Part III describes the main real-world applications based on ComputationalLinguistics techniques， including machine translation， information retrieval， infor-mation extraction， question answering， text summarization， term extraction， textdata mining， natural language interfaces， spoken dialogue systems， multimodal/multimedia systems， computer-aided language learning， and multilinguai on-linelanguage processing.

书籍目录

Preface

Abbreviations

Introduction

PART I FUNDAMENTALS

PART II PROCESSES, METHODS, AND RESOURCES

PART III APPLICATIONS.

作者简介

《牛津计算语言学手册》内容简介：《牛津计算语言学手册》是一部手册性的计算语言学专著，收录了包括语言学家、计算机专家和语言工程人员在内的50位学者撰写的综述性文章，全面地反映了国外计算语言学主要领域的最新成果，是我们了解国外计算语言学发展动向的一个窗口。 全书各章写作风格一致，内容协调，浑然一体，使用有趣的实例来介绍艰深的技术问题，而且尽量不使用繁难的数学公式，尤其适合文科背景的读者阅读。对于那些对计算语言学感兴趣和刚入门的读者而言，《牛津计算语言学手册》也是一本必备的参考书。

图书封面

---

 牛津计算语言学手册下载

---