{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T20:03:33Z","timestamp":1774037013178,"version":"3.50.1"},"reference-count":96,"publisher":"Cambridge University Press (CUP)","issue":"6","license":[{"start":{"date-parts":[[2020,10,27]],"date-time":"2020-10-27T00:00:00Z","timestamp":1603756800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":["cambridge.org"],"crossmark-restriction":true},"short-container-title":["Nat. Lang. Eng."],"published-print":{"date-parts":[[2021,11]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>This study systematically reviews existing approaches to unsupervised grammar induction in terms of their theoretical underpinnings, practical implementations and evaluation. Our motivation is to identify the influence of functional-cognitive schools of grammar on language processing models in computational linguistics. This is an effort to fill any gap between the theoretical school and the computational processing models of grammar induction. Specifically, the review aims to answer the following research questions: Which types of grammar theories have been the subjects of grammar induction? Which methods have been employed to support grammar induction? Which features have been used by these methods for learning? How were these methods evaluated? Finally, in terms of performance, how do these methods compare to one another? Forty-three studies were identified for systematic review out of which 33 described original implementations of grammar induction; three provided surveys and seven focused on theories and experiments related to acquisition and processing of grammar in humans. The data extracted from the 33 implementations were stratified into 7 different aspects of analysis: theory of grammar; output representation; how grammatical productivity is processed; how grammatical productivity is represented; features used for learning; evaluation strategy and implementation methodology. In most of the implementations considered, grammar was treated as a generative-formal system, autonomous and independent of meaning. The parser decoding was done in a non-incremental, head-driven fashion by assuming that all words are available for the parsing model and the output representation of the grammar learnt was hierarchical, typically a dependency or a constituency tree. However, the theoretical and experimental studies considered suggest that a usage-based, incremental, sequential system of grammar is more appropriate than the formal, non-incremental, hierarchical view of grammar. This gap between the theoretical as well as experimental studies on one hand and the computational implementations on the other hand should be addressed to enable further progress in computational grammar induction research.<\/jats:p>","DOI":"10.1017\/s1351324920000327","type":"journal-article","created":{"date-parts":[[2020,10,27]],"date-time":"2020-10-27T09:39:15Z","timestamp":1603791555000},"page":"647-689","update-policy":"https:\/\/doi.org\/10.1017\/policypage","source":"Crossref","is-referenced-by-count":4,"title":["A systematic review of unsupervised approaches to grammar induction"],"prefix":"10.1017","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9715-2953","authenticated-orcid":false,"given":"Vigneshwaran","family":"Muralidaran","sequence":"first","affiliation":[]},{"given":"Irena","family":"Spasi\u0107","sequence":"additional","affiliation":[]},{"given":"Dawn","family":"Knight","sequence":"additional","affiliation":[]}],"member":"56","published-online":{"date-parts":[[2020,10,27]]},"reference":[{"key":"S1351324920000327_ref76","first-page":"1077","volume-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Ponvert","year":"2011"},{"key":"S1351324920000327_ref5","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(74)90018-8"},{"key":"S1351324920000327_ref22","doi-asserted-by":"publisher","DOI":"10.3115\/1557835.1557845"},{"key":"S1351324920000327_ref32","article-title":"Learning syntactic constructions from raw corpora","author":"Edelman","year":"2005","journal-title":"29th Boston University Conference on Language Development"},{"key":"S1351324920000327_ref49","doi-asserted-by":"crossref","unstructured":"Jin, L. , Doshi-Velez, F. , Miller, T. , Schuler, W. and Schwartz, L. (2018). Unsupervised Grammar Induction with Depth-bounded PCFG. arXiv preprint arXiv:1802.08545.","DOI":"10.1162\/tacl_a_00016"},{"key":"S1351324920000327_ref18","volume-title":"Remarks on Nominalization","author":"Chomsky","year":"1968"},{"key":"S1351324920000327_ref72","doi-asserted-by":"publisher","DOI":"10.1075\/cal.3"},{"key":"S1351324920000327_ref41","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(03)00080-9"},{"key":"S1351324920000327_ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2004.01.002"},{"key":"S1351324920000327_ref81","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3007.001.0001"},{"key":"S1351324920000327_ref89","first-page":"961","volume-title":"Advances in Neural Information Processing Systems","author":"Solan","year":"2004"},{"key":"S1351324920000327_ref38","volume-title":"Generalized Phrase Structure Grammar","author":"Gazdar","year":"1985"},{"key":"S1351324920000327_ref95","first-page":"30","volume-title":"Proceedings of the 2nd workshop on Cognitive Modeling and Computational Linguistics","author":"Yang","year":"2011"},{"key":"S1351324920000327_ref25","doi-asserted-by":"publisher","DOI":"10.1075\/llsee.20.05dik"},{"key":"S1351324920000327_ref58","first-page":"154","article-title":"Cognitive semantics","volume":"119","author":"Lakoff","year":"1988","journal-title":"Meaning and Mental Representations"},{"key":"S1351324920000327_ref91","first-page":"751","volume-title":"Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics","author":"Spitkovsky","year":"2010"},{"key":"S1351324920000327_ref85","doi-asserted-by":"publisher","DOI":"10.3115\/976744.976784"},{"key":"S1351324920000327_ref78","volume-title":"Transformational Syntax: A Student\u2019s Guide to Chomsky\u2019s Extended Standard Theory","author":"Radford","year":"1981"},{"key":"S1351324920000327_ref20","volume-title":"Linguistic Nativism and the Poverty of the Stimulus","author":"Clark","year":"2010"},{"key":"S1351324920000327_ref71","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.an.13.100184.000525"},{"key":"S1351324920000327_ref53","unstructured":"Kitchenham, B. and Charters, S. (2007). Guidelines for performing systematic literature reviews in software engineering."},{"key":"S1351324920000327_ref88","first-page":"73","volume-title":"Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP","volume":"1","author":"Snyder","year":"2009"},{"key":"S1351324920000327_ref2","volume-title":"Evolutionary Computation (CEC), 2010 IEEE Congress on (pp. 1\u20138)","author":"Araujo","year":"2010"},{"key":"S1351324920000327_ref70","article-title":"An extensive review of tools for manual annotation of documents","author":"Neves","year":"2019","journal-title":"Briefings in Bioinformatics"},{"key":"S1351324920000327_ref42","first-page":"3153","volume-title":"LREC","author":"Hajic","year":"2012"},{"key":"S1351324920000327_ref65","first-page":"84","volume-title":"Proceedings of the NAACL-HLT Workshop on the Induction of Linguistic Structure","author":"Mare\u010dek","year":"2012"},{"key":"S1351324920000327_ref80","first-page":"813","volume-title":"Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing","author":"Rimell","year":"2009"},{"key":"S1351324920000327_ref87","volume-title":"Verbal Behavior","author":"Skinner","year":"2014"},{"key":"S1351324920000327_ref48","first-page":"157","volume-title":"Multidisciplinary Perspectives on Linguistic Competences","author":"Jensen","year":"2014)"},{"key":"S1351324920000327_ref4","volume-title":"Proceedings of the Boston University Conference on Language Development","author":"Berant","year":"2007"},{"key":"S1351324920000327_ref77","doi-asserted-by":"publisher","DOI":"10.1177\/0023830913484901"},{"key":"S1351324920000327_ref12","first-page":"39","volume-title":"Proc. of the AAAI Workshop on Probabilistic-Based Natural Language Processing Techniques","author":"Briscoe","year":"1992"},{"key":"S1351324920000327_ref56","first-page":"43","article-title":"Between usage-based and meaningfully-motivated grammatical rules: a psycholinguistic basis of applied cognitive grammar","volume":"131","author":"Kr\u00f3l-Markefka","year":"2014","journal-title":"Studia Linguistica Universitatis Iagellonicae Cracoviensis"},{"key":"S1351324920000327_ref46","first-page":"101","volume-title":"Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics","author":"Headden","year":"2009"},{"key":"S1351324920000327_ref23","doi-asserted-by":"publisher","DOI":"10.1163\/9781849500104"},{"key":"S1351324920000327_ref36","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511624582"},{"key":"S1351324920000327_ref84","first-page":"38","volume-title":"Proceedings of the Fourteenth Conference on Computational Natural Language Learning","author":"Santamaria","year":"2010"},{"key":"S1351324920000327_ref47","unstructured":"Jackendoff, R. (1977). X syntax: A study of phrase structure. Linguistic Inquiry Monographs 4. Cambridge, Mass., (2), pp. 1\u2013249."},{"key":"S1351324920000327_ref6","unstructured":"Bloomfield, L. (1962). Language. 1933. Holt, New York."},{"key":"S1351324920000327_ref86","first-page":"384","volume-title":"Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics","author":"Seginer","year":"2007"},{"key":"S1351324920000327_ref55","first-page":"478","volume-title":"Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics","author":"Klein","year":"2004"},{"key":"S1351324920000327_ref26","doi-asserted-by":"publisher","DOI":"10.1075\/cilt.75.09dik"},{"key":"S1351324920000327_ref30","volume-title":"Natural Language Processing and Knowledge Engineering (NLP-KE), 2011 7th International Conference on (pp. 314\u2013318)","author":"Dominguez","year":"2011"},{"key":"S1351324920000327_ref61","doi-asserted-by":"publisher","DOI":"10.1515\/9783110214369"},{"key":"S1351324920000327_ref44","doi-asserted-by":"publisher","DOI":"10.1075\/lal.17"},{"key":"S1351324920000327_ref3","unstructured":"Bates, E. and McWhinney, B. (1982). Functionalist approaches to grammar."},{"key":"S1351324920000327_ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-010-9199-1"},{"key":"S1351324920000327_ref96","doi-asserted-by":"publisher","DOI":"10.3115\/1596276.1596283"},{"key":"S1351324920000327_ref92","first-page":"19","volume-title":"Proceedings of the Fifteenth Conference on Computational Natural Language Learning","author":"Spitkovsky","year":"2011"},{"key":"S1351324920000327_ref66","first-page":"297","volume-title":"Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning","author":"Mare\u010dek","year":"2012"},{"key":"S1351324920000327_ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-2614"},{"key":"S1351324920000327_ref15","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1082"},{"key":"S1351324920000327_ref54","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00101"},{"key":"S1351324920000327_ref10","first-page":"438","volume-title":"Proceedings of 5th International Joint Conference on Natural Language Processing","author":"Boonkwan","year":"2011"},{"key":"S1351324920000327_ref67","unstructured":"Marques, T. and Beuls, K. (2016). Evaluation strategies for computational construction grammars. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pp. 1137\u20131146."},{"key":"S1351324920000327_ref93","first-page":"16","volume-title":"Proceedings of the NAACL-HLT Workshop on the Induction of Linguistic Structure","author":"Spitkovsky","year":"2012"},{"key":"S1351324920000327_ref28","doi-asserted-by":"publisher","DOI":"10.3765\/plsa.v2i0.4009"},{"key":"S1351324920000327_ref9","doi-asserted-by":"publisher","DOI":"10.1111\/j.1551-6709.2009.01031.x"},{"key":"S1351324920000327_ref29","doi-asserted-by":"publisher","DOI":"10.1017\/langcog.2016.7"},{"key":"S1351324920000327_ref1","first-page":"173","volume-title":"International Conference on Current Trends in Theory and Practice of Computer Science","author":"Adriaans","year":"2000"},{"key":"S1351324920000327_ref33","volume-title":"Proceedings of the Annual Meeting of the Cognitive Science Society","author":"Ellefson","year":"2000"},{"key":"S1351324920000327_ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-010-0201-1_1"},{"key":"S1351324920000327_ref64","doi-asserted-by":"publisher","DOI":"10.1016\/B0-08-044854-2\/02040-X"},{"key":"S1351324920000327_ref90","first-page":"60","volume-title":"Proceedings of TextGraphs-6: Graph-based Methods for Natural Language Processing","author":"S\u00f8gaard","year":"2011"},{"key":"S1351324920000327_ref31","article-title":"Rich syntax from a raw corpus: unsupervised does it","author":"Edelman","year":"2003","journal-title":"NIPS-2003 Workshop on Syntax, Semantics and Statistics"},{"key":"S1351324920000327_ref68","unstructured":"Matthiessen, C.M. and Halliday, M.A.K. (2009). Systemic functional grammar: a first step into the theory."},{"key":"S1351324920000327_ref73","doi-asserted-by":"publisher","DOI":"10.3115\/992567.992596"},{"key":"S1351324920000327_ref7","first-page":"865","volume-title":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics","author":"Bod","year":"2006"},{"key":"S1351324920000327_ref50","doi-asserted-by":"publisher","DOI":"10.1162\/coli.2007.33.3.437"},{"key":"S1351324920000327_ref35","volume-title":"Lexical-Functional Grammar","author":"Falk","year":"2011"},{"key":"S1351324920000327_ref16","doi-asserted-by":"publisher","DOI":"10.1515\/9783112316009"},{"key":"S1351324920000327_ref79","first-page":"721","volume-title":"Proceedings of the 22nd International Conference on Computational Linguistics","author":"Reichart","year":"2008"},{"key":"S1351324920000327_ref74","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.322.7278.98"},{"key":"S1351324920000327_ref51","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511597855.007"},{"key":"S1351324920000327_ref14","doi-asserted-by":"publisher","DOI":"10.3115\/1596276.1596299"},{"key":"S1351324920000327_ref19","volume-title":"Aspects of the Theory of Syntax","author":"Chomsky","year":"2014"},{"key":"S1351324920000327_ref37","article-title":"How hierarchical is language use?","author":"Frank","year":"2012","journal-title":"Proceedings of the Royal Society of London B: Biological Sciences"},{"key":"S1351324920000327_ref82","doi-asserted-by":"publisher","DOI":"10.1006\/jmla.2000.2759"},{"key":"S1351324920000327_ref13","volume-title":"Proceedings of the Annual Meeting of the Cognitive Science Society","author":"Brodsky","year":"2007"},{"key":"S1351324920000327_ref63","volume-title":"Statistically-Driven Computer Grammars of English: The IBM\/Lancaster Approach (No. 8)","author":"Leech","year":"1993"},{"key":"S1351324920000327_ref83","first-page":"19","volume-title":"Proceedings of the ACL 2010 Student Research Workshop","author":"Sangati","year":"2010"},{"key":"S1351324920000327_ref57","doi-asserted-by":"publisher","DOI":"10.2307\/2025464"},{"key":"S1351324920000327_ref75","volume-title":"Head-Driven Phrase Structure Grammar","author":"Pollard","year":"1994"},{"key":"S1351324920000327_ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-7552(98)00110-X"},{"key":"S1351324920000327_ref69","unstructured":"Moshier, M. (1988). Extensions to unification grammar for the description of programming languages."},{"key":"S1351324920000327_ref43","doi-asserted-by":"publisher","DOI":"10.1515\/9783110197532"},{"key":"S1351324920000327_ref34","volume-title":"Cognitive Linguistics","author":"Evans","year":"2006"},{"key":"S1351324920000327_ref40","doi-asserted-by":"publisher","DOI":"10.1075\/tsl.3"},{"key":"S1351324920000327_ref60","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780195331967.001.0001"},{"key":"S1351324920000327_ref39","first-page":"455","article-title":"Posterior sparsity in unsupervised dependency parsing","volume":"12","author":"Gillenwater","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"S1351324920000327_ref62","doi-asserted-by":"publisher","DOI":"10.1109\/69.842255"},{"key":"S1351324920000327_ref8","first-page":"1","volume-title":"Proceedings of the Workshop on Cognitive Aspects of Computational Language Acquisition","author":"Bod","year":"2007"},{"key":"S1351324920000327_ref59","volume-title":"Foundations of Cognitive Grammar: Theoretical Prerequisites","author":"Langacker","year":"1987"},{"key":"S1351324920000327_ref17","volume-title":"Aspects of the Theory of Syntax","author":"Chomsky","year":"1965"},{"key":"S1351324920000327_ref24","unstructured":"Dennis, S.J. (2005). An exemplar-based approach to unsupervised parsing."},{"key":"S1351324920000327_ref45","volume-title":"Introduction to Formal Language Theory","author":"Harrison","year":"1978"}],"container-title":["Natural Language Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S1351324920000327","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T13:33:33Z","timestamp":1635255213000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S1351324920000327\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,27]]},"references-count":96,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,11]]}},"alternative-id":["S1351324920000327"],"URL":"https:\/\/doi.org\/10.1017\/s1351324920000327","relation":{},"ISSN":["1351-3249","1469-8110"],"issn-type":[{"value":"1351-3249","type":"print"},{"value":"1469-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10,27]]},"assertion":[{"value":"\u00a9 The Author(s), 2020. Published by Cambridge University Press","name":"copyright","label":"Copyright","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}}]}}