Computational linguisticsis aninterdisciplinaryfield concerned with thecomputational modellingofnatural language,as well as the study of appropriate computational approaches to linguistic questions. In general, computational linguistics draws uponlinguistics,computer science,artificial intelligence,mathematics,logic,philosophy,cognitive science,cognitive psychology,psycholinguistics,anthropologyandneuroscience,among others.
Origins
editThe field overlapped withartificial intelligencesince the efforts in the United States in the 1950s to use computers to automatically translate texts from foreign languages, particularly Russian scientific journals, into English.[1]Since rule-based approaches were able to makearithmetic(systematic) calculations much faster and more accurately than humans, it was expected thatlexicon,morphology,syntaxandsemanticscan be learned using explicit rules, as well. After thefailure of rule-based approaches,David Hays[2]coined the term in order to distinguish the field from AI and co-founded both theAssociation for Computational Linguistics (ACL)and theInternational Committee on Computational Linguistics(ICCL) in the 1970s and 1980s. What started as an effort to translate between languages evolved into a much wider field ofnatural language processing.[3][4]
Annotated corpora
editIn order to be able to meticulously study theEnglish language,an annotated text corpus was much needed. The PennTreebank[5]was one of the most used corpora. It consisted of IBM computer manuals, transcribed telephone conversations, and other texts, together containing over 4.5 million words of American English, annotated using bothpart-of-speechtagging and syntactic bracketing.[6]
Japanese sentence corpora were analyzed and a pattern oflog-normalitywas found in relation to sentence length.[7]
Modeling language acquisition
editThe fact that duringlanguage acquisition,children are largely only exposed to positive evidence,[8]meaning that the only evidence for what is a correct form is provided, and no evidence for what is not correct,[9]was a limitation for the models at the time because the now availabledeep learningmodels were not available in late 1980s.[10]
It has been shown that languages can be learned with a combination of simple input presented incrementally as the child develops better memory and longer attention span,[11]which explained the long period oflanguage acquisitionin human infants and children.[11]
Robots have been used to test linguistic theories.[12]Enabled to learn as children might, models were created based on anaffordancemodel in which mappings between actions, perceptions, and effects were created and linked to spoken words. Crucially, these robots were able to acquire functioning word-to-meaning mappings without needing grammatical structure.
Using thePrice equationandPólya urndynamics, researchers have created a system which not only predicts future linguistic evolution but also gives insight into the evolutionary history of modern-day languages.[13]
Chomsky's theories
editChomsky's theories have influenced computational linguistics, particularly in understanding how infants learn complex grammatical structures, such as those described inChomsky normal form.[14]Attempts have been made to determine how an infant learns a "non-normal grammar" as theorized by Chomsky normal form.[9]Research in this area combines structural approaches with computational models to analyze largelinguistic corporalike the PennTreebank,helping to uncover patterns in language acquisition.[15]
See also
edit
- Artificial intelligence in fiction
- Collostructional analysis
- Computational lexicology
- Computational Linguistics(journal)
- Computational models of language acquisition
- Computational semantics
- Computational semiotics
- Computer-assisted reviewing
- Dialog systems
- Glottochronology
- Grammar induction
- Human speechome project
- Internet linguistics
- Lexicostatistics
- Natural language processing
- Natural language user interface
- Quantitative linguistics
- Semantic relatedness
- Semantometrics
- Systemic functional linguistics
- Translation memory
- Universal Networking Language
References
edit- ^John Hutchins:Retrospect and prospect in computer-based translation.Archived2008-04-14 at theWayback MachineProceedings of MT Summit VII, 1999, pp. 30–44.
- ^"Deceased members".ICCL members.Archived fromthe originalon 17 May 2017.Retrieved15 November2017.
- ^Natural Language Processing by Liz Liddy, Eduard Hovy, Jimmy Lin, John Prager, Dragomir Radev, Lucy Vanderwende, Ralph Weischedel
- ^Arnold B. Barach:Translating Machine1975: And the Changes To Come.
- ^Marcus, M. & Marcinkiewicz, M. (1993)."Building a large annotated corpus of English: The Penn Treebank"(PDF).Computational Linguistics.19(2): 313–330.Archived(PDF)from the original on 2022-10-09.
- ^Taylor, Ann (2003). "1".Treebanks.Spring Netherlands. pp. 5–22.
- ^Furuhashi, S. & Hayakawa, Y. (2012). "Lognormality of the Distribution of Japanese Sentence Lengths".Journal of the Physical Society of Japan.81(3): 034004.Bibcode:2012JPSJ...81c4004F.doi:10.1143/JPSJ.81.034004.
- ^Bowerman, M. (1988).The "no negative evidence" problem: How do children avoid constructing an overly general grammar. Explaining language universals.
- ^abBraine, M.D.S. (1971). On two types of models of the internalization of grammars. In D.I. Slobin (Ed.), The ontogenesis of grammar: A theoretical perspective. New York: Academic Press.
- ^Powers, D.M.W. & Turk, C.C.R. (1989).Machine Learning of Natural Language.Springer-Verlag.ISBN978-0-387-19557-5.
- ^abElman, Jeffrey L. (1993). "Learning and development in neural networks: The importance of starting small".Cognition.48(1): 71–99.CiteSeerX10.1.1.135.4937.doi:10.1016/0010-0277(93)90058-4.PMID8403835.S2CID2105042.
- ^Salvi, G.; Montesano, L.; Bernardino, A.; Santos-Victor, J. (2012). "Language bootstrapping: learning word meanings from the perception-action association".IEEE Transactions on Systems, Man, and Cybernetics - Part B: Cybernetics.42(3): 660–71.arXiv:1711.09714.doi:10.1109/TSMCB.2011.2172420.PMID22106152.S2CID977486.
- ^Gong, T.; Shuai, L.; Tamariz, M. & Jäger, G. (2012). E. Scalas (ed.)."Studying Language Change Using Price Equation and Pólya-urn Dynamics".PLOS ONE.7(3): e33171.Bibcode:2012PLoSO...733171G.doi:10.1371/journal.pone.0033171.PMC3299756.PMID22427981.
- ^Yogita, Bansal (2016)."Insight to Computational Linguistics"(PDF).International Journal 4.10. p. 94.RetrievedSeptember 22,2024.
- ^Yogita, Bansal (2016)."Insight to Computational Linguistics"(PDF).International Journal 4.10. p. 94.RetrievedSeptember 22,2024.
Further reading
edit- Bates, M (1995)."Models of natural language understanding".Proceedings of the National Academy of Sciences of the United States of America.92(22): 9977–9982.Bibcode:1995PNAS...92.9977B.doi:10.1073/pnas.92.22.9977.PMC40721.PMID7479812.
- Steven Bird, Ewan Klein, and Edward Loper (2009).Natural Language Processing with Python.O'Reilly Media.ISBN978-0-596-51649-9.
- Daniel Jurafsky and James H. Martin (2008).Speech and Language Processing,2nd edition. Pearson Prentice Hall.ISBN978-0-13-187321-6.
- Mohamed Zakaria KURDI (2016).Natural Language Processing and Computational Linguistics: speech, morphology, and syntax,Volume 1. ISTE-Wiley.ISBN978-1848218482.
- Mohamed Zakaria KURDI (2017).Natural Language Processing and Computational Linguistics: semantics, discourse, and applications,Volume 2. ISTE-Wiley.ISBN978-1848219212.
External links
edit
- Association for Computational Linguistics (ACL)
- CICLing annual conferences on Computational LinguisticsArchived2019-02-06 at theWayback Machine
- Computational Linguistics – Applications workshop
- Free online introductory book on Computational Linguisticsat theWayback Machine(archived January 25, 2008)
- Language Technology World
- Resources for Text, Speech and Language Processing
- The Research Group in Computational LinguisticsArchived2013-08-01 at theWayback Machine