computational linguistics

{{Short description|Use of computational tools for the study of linguistics}}

{{About|the scientific field|the journal|Computational Linguistics (journal)}}

{{Linguistics|Subfields2}}

Computational linguistics is an interdisciplinary field concerned with the computational modelling of natural language, as well as the study of appropriate computational approaches to linguistic questions. In general, computational linguistics draws upon linguistics, computer science, artificial intelligence, mathematics, logic, philosophy, cognitive science, cognitive psychology, psycholinguistics, anthropology and neuroscience, among others.

Origins

The field overlapped with artificial intelligence since 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.John Hutchins: [http://www.hutchinsweb.me.uk/MTS-1999.pdf Retrospect and prospect in computer-based translation.] {{Webarchive|url=https://web.archive.org/web/20080414141215/http://www.hutchinsweb.me.uk/MTS-1999.pdf |date=2008-04-14 }} Proceedings of MT Summit VII, 1999, pp. 30–44. Since rule-based approaches were able to make arithmetic (systematic) calculations much faster and more accurately than humans, it was expected that lexicon, morphology, syntax and semantics can be learned using explicit rules, as well. After the failure of rule-based approaches, David Hays{{cite web|url=http://nlp.shef.ac.uk/iccl/committee.html#deceased|title=Deceased members|website=ICCL members|access-date=15 November 2017|ref=ICCLmembers|archive-date=17 May 2017|archive-url=https://web.archive.org/web/20170517235543/http://nlp.shef.ac.uk/iccl/committee.html#deceased|url-status=dead}} coined the term in order to distinguish the field from AI and co-founded both the Association for Computational Linguistics (ACL) and the International 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 of natural language processing.[http://www-nlpir.nist.gov/MINDS/FINAL/NLP.web.pdf Natural Language Processing by Liz Liddy, Eduard Hovy, Jimmy Lin, John Prager, Dragomir Radev, Lucy Vanderwende, Ralph Weischedel]Arnold B. Barach: [https://www.flickr.com/photos/bostworld/2152048032/in/set-72157603898383698/ Translating Machine] 1975: And the Changes To Come.

Annotated corpora

In order to be able to meticulously study the English language, an annotated text corpus was much needed. The Penn Treebank{{cite journal|author1=Marcus, M.|author2=Marcinkiewicz, M.|name-list-style=amp|year=1993|url=https://www.aclweb.org/anthology/J/J93/J93-2004.pdf |archive-url=https://ghostarchive.org/archive/20221009/https://www.aclweb.org/anthology/J/J93/J93-2004.pdf |archive-date=2022-10-09 |url-status=live|title=Building a large annotated corpus of English: The Penn Treebank|journal=Computational Linguistics|volume=19|issue=2|pages=313–330}} 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 both part-of-speech tagging and syntactic bracketing.{{cite book|last1=Taylor|first1=Ann|title=Treebanks|date=2003|publisher=Spring Netherlands|pages=5–22|chapter=1}}

Japanese sentence corpora were analyzed and a pattern of log-normality was found in relation to sentence length.{{cite journal|author1=Furuhashi, S.|author2=Hayakawa, Y. |name-list-style=amp|year=2012|title=Lognormality of the Distribution of Japanese Sentence Lengths|journal=Journal of the Physical Society of Japan|volume=81|issue=3|page=034004|doi=10.1143/JPSJ.81.034004|bibcode=2012JPSJ...81c4004F }}

Modeling language acquisition

The fact that during language acquisition, children are largely only exposed to positive evidence,Bowerman, M. (1988). [http://pubman.mpdl.mpg.de/pubman/item/escidoc:468143:4/component/escidoc:532427/bowerman_1988_The-No.pdf The "no negative evidence" problem: How do children avoid constructing an overly general grammar. Explaining language universals]. meaning that the only evidence for what is a correct form is provided, and no evidence for what is not correct,Braine, 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. was a limitation for the models at the time because the now available deep learning models were not available in late 1980s.Powers, D.M.W. & Turk, C.C.R. (1989). Machine Learning of Natural Language. Springer-Verlag. {{ISBN|978-0-387-19557-5}}.

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,{{cite journal|title= Learning and development in neural networks: The importance of starting small|journal= Cognition|volume= 48|issue= 1|pages= 71–99|doi= 10.1016/0010-0277(93)90058-4|pmid= 8403835|year= 1993|last1= Elman|first1= Jeffrey L.|s2cid= 2105042|citeseerx= 10.1.1.135.4937}} which explained the long period of language acquisition in human infants and children.

Robots have been used to test linguistic theories.{{cite journal | last1 = Salvi | first1 = G. | last2 = Montesano | first2 = L. | last3 = Bernardino | first3 = A. | last4 = Santos-Victor | first4 = J. | year = 2012 | title = Language bootstrapping: learning word meanings from the perception-action association | journal = IEEE Transactions on Systems, Man, and Cybernetics - Part B: Cybernetics | volume = 42 | issue = 3| pages = 660–71 | doi = 10.1109/TSMCB.2011.2172420 | pmid = 22106152 | arxiv = 1711.09714 | s2cid = 977486 }} Enabled to learn as children might, models were created based on an affordance model 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 the Price equation and Pólya urn dynamics, researchers have created a system which not only predicts future linguistic evolution but also gives insight into the evolutionary history of modern-day languages.{{cite journal|author1=Gong, T.|author2=Shuai, L.|author3=Tamariz, M.|author4=Jäger, G.|name-list-style=amp|year=2012|title=Studying Language Change Using Price Equation and Pólya-urn Dynamics|editor=E. Scalas|journal=PLOS ONE|volume=7|issue=3|page=e33171|doi=10.1371/journal.pone.0033171|pmid=22427981|pmc=3299756|bibcode=2012PLoSO...733171G|doi-access=free}}

Chomsky's theories

Noam Chomsky's theories have influenced computational linguistics, particularly in understanding how infants learn complex grammatical structures, such as those described in Chomsky normal form.{{cite web |last1=Yogita |first1=Bansal |title=Insight to Computational Linguistics |url=https://d1wqtxts1xzle7.cloudfront.net/50283410/ijeter034102016-libre.pdf?1479039496=&response-content-disposition=inline%3B+filename%3DInsight_to_Computational_Linguistics.pdf&Expires=1727013507&Signature=OpBNq-Ocozu3StViVzaoeet1B7yVJUvnnLUxYpQKaTUr71Cho6YFoTZPv2k6ZzXtkxuZ3ViZNDJp~t5nLAyLxLk0mxGR6oVMQK4Rk68RaaCZVebBMvFMqKyRHGhwpbFLMbibo5eD7MHZQBPAxDwjBDGtX0TjORdrQ2XUCLw~vM7AtWsP3wtTj-TeHXSfQiL8DiyuvjEZEoqQ1NGhE2S1po~kTs5Eov-WFvYrfm4McdL~ztLUTdUmHyd3ntg0zI9pNPZG7CtouiHWtEA26fXOZEbD5Qv9C1~gnV8VTSLzxWSMwEe3od6vPKoW1jlngnLLK9VoldGapnaUjJtWtW2MKw__&Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA |publisher=International Journal 4.10 |access-date=September 22, 2024 |page=94 |date=2016}} Attempts have been made to determine how an infant learns a "non-normal grammar" as theorized by Chomsky normal form. Research in this area combines structural approaches with computational models to analyze large linguistic corpora like the Penn Treebank, helping to uncover patterns in language acquisition.{{cite web |last1=Yogita |first1=Bansal |title=Insight to Computational Linguistics |url=https://d1wqtxts1xzle7.cloudfront.net/50283410/ijeter034102016-libre.pdf?1479039496=&response-content-disposition=inline%3B+filename%3DInsight_to_Computational_Linguistics.pdf&Expires=1727013507&Signature=OpBNq-Ocozu3StViVzaoeet1B7yVJUvnnLUxYpQKaTUr71Cho6YFoTZPv2k6ZzXtkxuZ3ViZNDJp~t5nLAyLxLk0mxGR6oVMQK4Rk68RaaCZVebBMvFMqKyRHGhwpbFLMbibo5eD7MHZQBPAxDwjBDGtX0TjORdrQ2XUCLw~vM7AtWsP3wtTj-TeHXSfQiL8DiyuvjEZEoqQ1NGhE2S1po~kTs5Eov-WFvYrfm4McdL~ztLUTdUmHyd3ntg0zI9pNPZG7CtouiHWtEA26fXOZEbD5Qv9C1~gnV8VTSLzxWSMwEe3od6vPKoW1jlngnLLK9VoldGapnaUjJtWtW2MKw__&Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA |publisher=International Journal 4.10 |access-date=September 22, 2024 |page=94 |date=2016}}

See also

References

{{reflist|30em}}

Further reading

{{Refbegin}}

  • {{cite journal | last1 = Bates | first1 = M | year = 1995 | title = Models of natural language understanding | journal = Proceedings of the National Academy of Sciences of the United States of America | volume = 92 | issue = 22| pages = 9977–9982 | doi=10.1073/pnas.92.22.9977| pmid = 7479812 | pmc = 40721| bibcode = 1995PNAS...92.9977B | doi-access = free }}
  • Steven Bird, Ewan Klein, and Edward Loper (2009). Natural Language Processing with Python. O'Reilly Media. {{ISBN|978-0-596-51649-9}}.
  • Daniel Jurafsky and James H. Martin (2008). Speech and Language Processing, 2nd edition. Pearson Prentice Hall. {{ISBN|978-0-13-187321-6}}.
  • Mohamed Zakaria KURDI (2016). Natural Language Processing and Computational Linguistics: speech, morphology, and syntax, Volume 1. ISTE-Wiley. {{ISBN|978-1848218482}}.
  • Mohamed Zakaria KURDI (2017). Natural Language Processing and Computational Linguistics: semantics, discourse, and applications, Volume 2. ISTE-Wiley. {{ISBN| 978-1848219212}}.

{{Refend}}