2003 TheOxfordHandbookOfCompLing

• (Mitkov, 2003) ⇒ Ruslan Mitkov. (2003). “The Oxford Handbook of Computational Linguistics.” In: Oxford University Press. ISBN:019927634X

Subjects Headings: Computational Linguistics, Survey.

Quotes

Publisher Blurb

• Thirty-eight chapters, comissioned from experts all over the world, describe major concepts, methods, and applications in computational linguistics.
• Part I, Linguistic Fundamentals, provides an overview of the field suitable for senior undergraduates and non-specialists from other fields of linguistics and related disciplines.
• Part II describes current tasks, techniques, and tools in Natural Language Processing and aims to meet the needs of post-doctoral workers and others embarking on computational language research.
• Part III surveys current applications.

Part I: Fundamentals

• 1. Phonology, Steven Bird.
• 2. Morphology, Harald Trost
• 3. Computational Lexicography, Patrick Hanks.
• 4. Syntax, Ronald M. Kaplan
• 5. Semantics, Shalom Lappin
• 6. Discourse, Allan Ramsay
• 7. Pragmatics and Dialogue, Geoffrey N. Leech and Martin Weisser
• 8. Formal Grammars and Languages, Carlos Martin-Vide
• 9. Complexity, Bob Carpenter

Part II: Processes, Methods, and Resources

• 10. (Mikheev, 2003) ⇒ Andrei Mikheev. (2003). “Text Segmentation.” In: (Mitkov, 2003).
• 11. Part-of-Speech Tagging, Atro Voutilainen
• 12. Parsing, John Carroll
• 13. (Stevenson & Wilks, 2003) ⇒ Mark Stevenson, and Yorick Wilks. (2003). “Word-Sense Disambiguation.” In: (Mitkov, 2003).
• 14. Anaphora Resolution, Ruslan Mitkov.
• 15. Natural Language Generation, John Bateman and Michael Zock
• 16. Speech Recognition, Lori Lamel and Jean-Luc Gauvain
• 17. Text-to-Speech Synthesis, Thierry Dutoit and Yannis Stylianou
• 18. Finite-State Technology, Lauri Karttunen
• 19. Statistical Methods, Christer Samuelsson
• 20. Machine Learning, Raymond Mooney.
• 21. Lexical Knowledge Acquisition, Yuji Matsumoto
• 22. Evaluation, Lynette Hirschman and Inderjeet Mani.
• 23. Sublanguages and Controlled Languages, Richard I. Kittredge
• 24. Corpora, Tony McEnery
• 25. Ontologies, Piek Vossen
• 26. Tree-Adjoining Grammars, Aravind K. Joshi

Part III: Applications

• 27. Machine Translation: General Overview, John Hutchins
• 28. Machine Translation: Latest Developments, Harold Somers
• 29. Information Retrieval, Evelyne Tzoukermann, Judith L. Klavans and Tomek Strzalkowski
• 30. (Grishman, 2003) ⇒ Ralph Grishman. (2003). “ iInformation Extraction.
• 31. Question Answering, Sanda M. Harabagiu and Dan Moldovan.
• 32. Text Summarization, Eduard Hovy.
• 33. (Jacquemin & Bourigault, 2003) ⇒ Christian Jacquemin and Didier Bourigault. (2003). “Term Extraction and Automatic Indexing. In: (Mitkov, 2003).
• 34. Text Data Mining, Marti A. Hearst.
• 35. Natural Language Interaction, Ion Androutsopoulos and Maria Aretoulaki
• 36. Natural Language in Multimodal and Multimedia Systems, Elisabeth Andre
• 37. Natural Language Processing in Computer-Aided Language Learning, John Nerbonne
• 38. Multilingual On-Line Natural Language Processing, Gregory Grefenstette and Frederique Segond

Glossary

• base form: The part of a word that carries its meaning; it severs as the bases for all inflectional forms of the word.
• computational terminology: The computer-assisted acquisition, maintenance, or exploitation of terminological data.
• inflection: (1) The morphological process of adding inflections to base forms of words, as required by syntactic context; (ii) a linguistic element that is added to or alters the base form of a word, as require by particular syntactic contexts. Inflections
• lemmatization: The process of grouping the inflected forms of a word together under a base form, or of recovering the base form from an inflected form, e.g. grouping the inflected forms 'run','runs','running','ran' under the base form 'run'.
• lexical entry: A word or phrase in a lexicon, used as a peg on which to hang information about part of speech, subcategorization, meaning, pronunciation, links to related terms, and/or any of various other kinds of information.
• lexical semantic network: A set of terms defined solely in terms of relations to each other.
• lexical semantic relation: Semantic relations between lexicalizations in a language.
• lexical transducer: A finite-state transducer for morphological analysis and generation. It maps inflected forms into the corresponding lexical forms (=lemmas), and vice versa.
• lexical variability: The property of words according to which a single word may be used with basically the same meaning in many difference contexts, with different implications. For example, the verb file in filing a story, filing a lawsuit, and filing a flight plan has basically the same meaning ('place on record') but different implications.
• lexicalization: The process of generating an appropriate lexical item for given semantic content - typically a phase of the automatic text generation process.
• lexicography: The compilation of an inventory of the lexicon of a language, typically including a statement about some or all of the following features with record to each lexical entry: orthography, pronunciation, inflected forms, word class (part of speech), meaning(s) or translations, usage, phraseology, and history or origin.
• term: A lexical unit, typically one validated for entry in an application-oriented terminological resource describing the vocabulary of a specialized subject field.
• term acquisition: Automatic discovery of previously unrecognized terms in corpora.
• term frequency (tf): A measurement of the frequency of a word or term within a particular document. Term frequency reflects how well that term describes the document contents.
• term recognition: Automatic recognition of term and variant occurrences in corpora.
• term spotting: Extracting of occurrences of terms or variants from text documents.
• terminology management: The computer-based process of creating, maintaining, and searching multilingual databases of terminology.
• word-sense disambiguation: The process of identifying the meanings of words in context.
• word-token: An occurrence in text of a word from a language vocabulary. Compare word-type.
• word-type: A word in a language vocabulary, as opposed to its specific occurrence in text. Compare word-token.

References

---

,

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2003 TheOxfordHandbookOfCompLing	Ruslan Mitkov			The Oxford Handbook of Computational Linguistics		Oxford University Press	http://books.google.com/books?id=OaClhre-vW4C			2003