{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T01:02:52Z","timestamp":1648515772064},"reference-count":37,"publisher":"Cambridge University Press (CUP)","issue":"4","license":[{"start":{"date-parts":[[2010,10,11]],"date-time":"2010-10-11T00:00:00Z","timestamp":1286755200000},"content-version":"unspecified","delay-in-days":10,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Nat. Lang. Eng."],"published-print":{"date-parts":[[2010,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Lapata and Brew (<jats:italic>Computational Linguistics<\/jats:italic>, vol. 30, 2004, pp. 295\u2013313) (hereafter LB04) obtain from untagged texts a statistical prior model that is able to generate class preferences for ambiguous Lewin (<jats:italic>English Verb Classes and Alternations: A Preliminary Investigation<\/jats:italic>, 1993, University of Chicago Press) verbs (hereafter Levin). They also show that their informative priors, incorporated into a Naive Bayes classifier deduced from hand-tagged data (HTD), can aid in verb class disambiguation. We re-analyse LB04's prior model and show that a single factor (the joint probability of class and frame) determines the predominant class for a particular verb in a particular frame. This means that the prior model cannot be sensitive to fine-grained lexical distinctions between different individual verbs falling in the same class.<\/jats:p><jats:p>We replicate LB04's supervised disambiguation experiments on large-scale data, using deep parsers rather than the shallow parser of LB04. In addition, we introduce a method for training our classifier without using HTD. This relies on knowledge of Levin class memberships to move information from unambiguous to ambiguous instances of each class. We regard this system as unsupervised because it does not rely on human annotation of individual verb instances. Although our unsupervised verb class disambiguator does not match the performance of the ones that make use of HTD, it consistently outperforms the random baseline model. Our experiments also demonstrate that the informative priors derived from untagged texts help improve the performance of the classifier trained on untagged data.<\/jats:p>","DOI":"10.1017\/s1351324910000136","type":"journal-article","created":{"date-parts":[[2010,10,11]],"date-time":"2010-10-11T11:13:10Z","timestamp":1286795590000},"page":"391-415","source":"Crossref","is-referenced-by-count":1,"title":["Class-based approach to disambiguating Levin verbs"],"prefix":"10.1017","volume":"16","author":[{"given":"JIANGUO","family":"LI","sequence":"first","affiliation":[]},{"given":"CHRIS","family":"BREW","sequence":"additional","affiliation":[]}],"member":"56","published-online":{"date-parts":[[2010,10,11]]},"reference":[{"key":"S1351324910000136_ref13","first-page":"1","article-title":"A general feature space for automatic verb classification","volume":"1","author":"Joanis","year":"2007","journal-title":"Natural Language Engineering"},{"key":"S1351324910000136_ref12","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324902003005"},{"key":"S1351324910000136_ref27","doi-asserted-by":"publisher","DOI":"10.1162\/089120101317066122"},{"key":"S1351324910000136_ref1","unstructured":"Carroll G. , and Rooth M. 1998. Valence induction with a head-lexicalized PCFG. In Proceedings of the 1998 Conference on EMNLP, pp. 58\u201363."},{"key":"S1351324910000136_ref29","doi-asserted-by":"crossref","unstructured":"Pado S. , and Lapata M. 2003. Constructing semantic space from parsed corpora. In Proceedings of the 41st Annual Meeting of ACL, pp. 545\u2013552.","DOI":"10.3115\/1075096.1075113"},{"key":"S1351324910000136_ref5","doi-asserted-by":"publisher","DOI":"10.1353\/lan.1991.0021"},{"key":"S1351324910000136_ref36","unstructured":"Swier R. , and Stevenson S. 2004. Unsupervised semantic role labelling. In Proceedings of the 2004 Conference on EMNLP, pp. 95\u2013102."},{"key":"S1351324910000136_ref23","unstructured":"Li J. , and Brew C. 2008. Which are the best features for automatic verb classification. In Proceedings of the 46th Annual Meeting of ACL, pp. 434\u2013442."},{"key":"S1351324910000136_ref3","doi-asserted-by":"publisher","DOI":"10.1023\/A:1002497503122"},{"key":"S1351324910000136_ref35","doi-asserted-by":"crossref","unstructured":"Shi L. , and Mihalcea R. 2005. Put pieces together: combining FrameNet, VerbNet and WordNet for robust semantic parsing. In Proceedings of the 6th International Conference on Computational Linguistics and Intelligent Text Processing, pp. 100\u2013111.","DOI":"10.1007\/978-3-540-30586-6_9"},{"key":"S1351324910000136_ref7","doi-asserted-by":"publisher","DOI":"10.1162\/089120102760275983"},{"key":"S1351324910000136_ref2","unstructured":"Charniak E. 2000. A maximum-entropy-inspired parser. In Proceedings of the 2000 Conference of NAACL, pp. 132\u2013139."},{"key":"S1351324910000136_ref4","doi-asserted-by":"crossref","unstructured":"Dang H. , Kipper K. , Palmer M. , and Rosenzweig J. 1998. Investigating regular sense extensions based on intersective Levin classes. In Proceedings of the 17th International Conference on COLING and 36th Annual Meeting of ACL, pp. 293\u2013299.","DOI":"10.3115\/980845.980893"},{"key":"S1351324910000136_ref6","first-page":"61","article-title":"Accurate methods for the statistics of surprise and coincidence","volume":"19","author":"Dunning","year":"1993","journal-title":"Computational Linguistics"},{"key":"S1351324910000136_ref9","volume-title":"Semantics and Syntactic Regularity","author":"Green","year":"1974"},{"key":"S1351324910000136_ref10","doi-asserted-by":"crossref","unstructured":"Henderson J. 2003. Inducing history representations for broad-coverage statistical parsing. In Proceedings of the 2003 Joint Meeting of NAACL\/HLT, pp. 103\u2013110.","DOI":"10.3115\/1073445.1073459"},{"key":"S1351324910000136_ref11","unstructured":"Hoste V. , Kool A. , and Daelemans W. 2001. Classifier optimization and combination in the English all words tasks. In Proceedings of the SENSEVAL-2 Workshop, pp. 84\u201386."},{"key":"S1351324910000136_ref14","unstructured":"Kipper K. , Dang H. , and Palmer M. 2000. Class-Based Construction of a Verb Lexicon. In Proceedings of AAAI\/IAAI, pp. 691\u2013696."},{"key":"S1351324910000136_ref15","volume-title":"Subcategorization Acquisition","author":"Korhonen","year":"2002"},{"key":"S1351324910000136_ref16","doi-asserted-by":"crossref","unstructured":"Korhonen A. , Krymolowski Y. , and Marx Z. 2003. Clustering polysemic subcategorization frame distributions semantically. In Proceedings of the 41st Annual Meeting of ACL, pp. 64\u201371.","DOI":"10.3115\/1075096.1075105"},{"key":"S1351324910000136_ref17","doi-asserted-by":"crossref","unstructured":"Korhonen A. , and Preiss J. 2003. Improving subcategorization acquisition using word sense disambiguation. In Proceedings of the 41st Annual Meeting of ACL, pp. 48\u201355.","DOI":"10.3115\/1075096.1075103"},{"key":"S1351324910000136_ref18","doi-asserted-by":"crossref","unstructured":"Lapata M. 1999. Acquiring lexical generalizations from corpora: a case study for diathesis alternations. In Proceedings of the 37th Annual Meeting of ACL, pp. 397\u2013404.","DOI":"10.3115\/1034678.1034740"},{"key":"S1351324910000136_ref19","doi-asserted-by":"publisher","DOI":"10.1162\/089120104773633385"},{"key":"S1351324910000136_ref20","first-page":"147","article-title":"Using corpus statistics and WordNet relations for sense identification","volume":"24","author":"Leacock","year":"1998","journal-title":"Computational Linguistics"},{"key":"S1351324910000136_ref21","doi-asserted-by":"crossref","unstructured":"Lee K. , and Ng H. 2002. An empirical evaluation of knowledge sources and learning algorithm for word sense disambiguation. In Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing, pp. 41\u201348.","DOI":"10.3115\/1118693.1118699"},{"key":"S1351324910000136_ref22","volume-title":"English Verb Classes and Alternations: A Preliminary Investigation","author":"Levin","year":"1993"},{"key":"S1351324910000136_ref24","doi-asserted-by":"crossref","unstructured":"Lin D. 1998. Automatic retrieval and clustering of similar words. In Proceedings of the 17th International Conference on COLING and 36th Annual Meeting of ACL, pp. 768\u2013774.","DOI":"10.3115\/980432.980696"},{"key":"S1351324910000136_ref30","doi-asserted-by":"publisher","DOI":"10.1023\/A:1002613125904"},{"key":"S1351324910000136_ref25","doi-asserted-by":"crossref","unstructured":"McCarthy D. , Koeling R. , Weeds J. , and Carroll J. 2004. Finding predominant senses in untagged text. In Proceedings of the 42nd Annual Meeting of ACL, pp. 280\u2013287.","DOI":"10.3115\/1218955.1218991"},{"key":"S1351324910000136_ref26","unstructured":"Merlo P. , Joanis E. , and Henderson J. 2005. Unsupervised verb class disambiguation based on diathesis alternations, Manuscript."},{"key":"S1351324910000136_ref31","first-page":"573","article-title":"An improved method for deriving word meaning from lexical co-occurrence","volume":"7","author":"Rohde","year":"2004","journal-title":"Cognitive Psychology"},{"key":"S1351324910000136_ref32","doi-asserted-by":"crossref","unstructured":"Schulte im Walde S. 2000. Clustering verbs semantically according to alternation behavior. In Proceedings of the 18th International Conference on COLING, pp. 747\u2013753.","DOI":"10.3115\/992730.992754"},{"key":"S1351324910000136_ref33","first-page":"97","article-title":"Automatic word sense disambiguation","volume":"24","author":"Schutze","year":"1998","journal-title":"Computational Linguistics"},{"key":"S1351324910000136_ref34","unstructured":"Shen D. , and Lapata M. 2007. Using semantic roles to improve question answering. In Proceedings of the 2007 Conference on EMNLP-CoNLL, pp. 12\u201321."},{"key":"S1351324910000136_ref28","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1017\/S1351324901002728","article-title":"Applied morphological processing of English","volume":"7","author":"Minnen","year":"2000","journal-title":"Natural Language Engineering"},{"key":"S1351324910000136_ref37","doi-asserted-by":"crossref","unstructured":"Yarowsky D. 1992. Word-sense disambiguation using statistical models of Roget's categories trained on large corpora. In Proceedings of the 15th International Conference on COLING, pp. 88\u201394.","DOI":"10.3115\/992133.992140"},{"key":"S1351324910000136_ref8","volume-title":"Constructions","author":"Goldberg","year":"1995"}],"container-title":["Natural Language Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S1351324910000136","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,4,27]],"date-time":"2019-04-27T17:14:29Z","timestamp":1556385269000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S1351324910000136\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,10]]},"references-count":37,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2010,10]]}},"alternative-id":["S1351324910000136"],"URL":"https:\/\/doi.org\/10.1017\/s1351324910000136","relation":{},"ISSN":["1351-3249","1469-8110"],"issn-type":[{"value":"1351-3249","type":"print"},{"value":"1469-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,10]]}}}