computational linguistics
In plain wordsThe science of human language studied with computers: using computational models to understand how language works, and building the language technology that grows out of that understanding.
The scientific study of language by means of computation: writing explicit, testable computer models of how sound systems, word structure, syntax, meaning and discourse work, and creating the algorithms and resources such models need, such as grammars, corporacorpus, n.: A large collection of written or spoken language, gathered so that people or computers can study it or learn from it — like a library assembled for a language model., treebanks and lexicons. In practice and in its publication venues it overlaps almost entirely with natural language processingnatural language processing, n.: The field that teaches computers to handle human language — to read, interpret, translate, summarize and produce text and speech. It is one of the oldest and largest areas of artificial intelligence.; where a distinction is drawn, computational linguistics leans toward scientific questions about language and linguistic theory, while NLP leans toward engineering systems that perform useful tasks. Its main society, the Association for Computational Linguistics (ACL), runs the field's leading conferences and its journal, Computational Linguistics.
Her computational linguistics thesis used language models to test theories of how children learn verb agreement.
Origin
The name is credited to David Hays, a machine-translation researcher at the RAND Corporation from 1955 to 1968, for the field growing out of machine translation; the year he first used it is not recorded. It was in use by 1962, when the Association for Machine Translation and Computational Linguistics was founded; the society became the Association for Computational Linguistics in 1968.
Related
- natural language processingnatural language processing, n.: The field that teaches computers to handle human language — to read, interpret, translate, summarize and produce text and speech. It is one of the oldest and largest areas of artificial intelligence.
- machine translationmachine translation, n.: Software that renders writing or speech in one language into another language, as online translation services and phone translation apps do.
- corpuscorpus, n.: A large collection of written or spoken language, gathered so that people or computers can study it or learn from it — like a library assembled for a language model.
- syntactic parsingsyntactic parsing, n.: Working out the grammatical structure of a sentence — which words group together and which word modifies which — usually drawn as a tree.
- part-of-speech taggingpart-of-speech tagging, n.: Labeling each word in a sentence with its grammatical role — noun, verb, adjective and so on — as in 'Time (noun) flies (verb) like (preposition) an arrow'.
- distributional hypothesisdistributional hypothesis, n.: The idea that words found in similar company — surrounded by similar words — tend to be similar in meaning, the insight that lets computers learn something about word meaning from large amounts of text alone.
- natural language processingnatural language processing, n.: The field that teaches computers to handle human language — to read, interpret, translate, summarize and produce text and speech. It is one of the oldest and largest areas of artificial intelligence.
Mentioned in
natural language processingnatural language processing, n.: The field that teaches computers to handle human language — to read, interpret, translate, summarize and produce text and speech. It is one of the oldest and largest areas of artificial intelligence., part-of-speech taggingpart-of-speech tagging, n.: Labeling each word in a sentence with its grammatical role — noun, verb, adjective and so on — as in 'Time (noun) flies (verb) like (preposition) an arrow'., syntactic parsingsyntactic parsing, n.: Working out the grammatical structure of a sentence — which words group together and which word modifies which — usually drawn as a tree., word sense disambiguationword sense disambiguation, n.: Working out which meaning of a word is intended in context — whether 'bank' means a riverside or a place that keeps money.