{"id":"https://openalex.org/W2150208223","doi":"https://doi.org/10.3115/1075096.1075105","title":"Clustering polysemic subcategorization frame distributions semantically","display_name":"Clustering polysemic subcategorization frame distributions semantically","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2150208223","doi":"https://doi.org/10.3115/1075096.1075105","mag":"2150208223"},"language":"en","primary_location":{"id":"doi:10.3115/1075096.1075105","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1075096.1075105","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1075096.1075105","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st Annual Meeting on Association for Computational Linguistics  - ACL '03","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1075096.1075105","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081393566","display_name":"Anna Korhonen","orcid":"https://orcid.org/0000-0002-3692-3144"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Anna Korhonen","raw_affiliation_strings":["University of Cambridge, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088249499","display_name":"Yuval Krymolowski","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuval Krymolowski","raw_affiliation_strings":["University of Edinburgh, Edinburgh, Scotland, UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, Scotland, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054293786","display_name":"Zvika Marx","orcid":null},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Zvika Marx","raw_affiliation_strings":["The Hebrew University, Jerusalem, Israel"],"affiliations":[{"raw_affiliation_string":"The Hebrew University, Jerusalem, Israel","institution_ids":["https://openalex.org/I197251160"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081393566"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":10.2952,"has_fulltext":true,"cited_by_count":82,"citation_normalized_percentile":{"value":0.98182084,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"1","issue":null,"first_page":"64","last_page":"71"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/subcategorization","display_name":"Subcategorization","score":0.9540256857872009},{"id":"https://openalex.org/keywords/polysemy","display_name":"Polysemy","score":0.8739721775054932},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7817218899726868},{"id":"https://openalex.org/keywords/information-bottleneck-method","display_name":"Information bottleneck method","score":0.7797114849090576},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7473191022872925},{"id":"https://openalex.org/keywords/verb","display_name":"Verb","score":0.695065438747406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6363784670829773},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6342013478279114},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5875537395477295},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5496129989624023},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5475221872329712},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.42840576171875}],"concepts":[{"id":"https://openalex.org/C70845037","wikidata":"https://www.wikidata.org/wiki/Q6980760","display_name":"Subcategorization","level":3,"score":0.9540256857872009},{"id":"https://openalex.org/C2780276568","wikidata":"https://www.wikidata.org/wiki/Q191928","display_name":"Polysemy","level":2,"score":0.8739721775054932},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7817218899726868},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.7797114849090576},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7473191022872925},{"id":"https://openalex.org/C2776397901","wikidata":"https://www.wikidata.org/wiki/Q24905","display_name":"Verb","level":2,"score":0.695065438747406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6363784670829773},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6342013478279114},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5875537395477295},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5496129989624023},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5475221872329712},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.42840576171875},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.3115/1075096.1075105","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1075096.1075105","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1075096.1075105","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st Annual Meeting on Association for Computational Linguistics  - ACL '03","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.11.2445","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.11.2445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cl.cam.ac.uk/users/alk23/ACL-clustering.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.136.6977","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.136.6977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ixa.si.ehu.es/ixa/local/meaning-workshop/papers/korhonen.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.14.6736","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.14.6736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ltg.ed.ac.uk/~ykrymolo/papers/clus-poly-scf.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.3.1497","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.3.1497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/acl2003/main/pdfs/KorhonenKrymolowski.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.63.4302","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.63.4302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cl.cam.ac.uk/users/alk23/ACL-clustering.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.9.6562","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.9.6562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/P/P03/P03-1009.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.9.9965","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.9.9965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/acl2003/main/ps/KorhonenKrymolowski.ps","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1075096.1075105","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1075096.1075105","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1075096.1075105","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st Annual Meeting on Association for Computational Linguistics  - ACL '03","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4399999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2150208223.pdf","grobid_xml":"https://content.openalex.org/works/W2150208223.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1556182881","https://openalex.org/W1686946872","https://openalex.org/W1974157030","https://openalex.org/W2002373856","https://openalex.org/W2008172256","https://openalex.org/W2040300040","https://openalex.org/W2040985480","https://openalex.org/W2076433133","https://openalex.org/W2088198454","https://openalex.org/W2102381086","https://openalex.org/W2105822493","https://openalex.org/W2107241511","https://openalex.org/W2114332321","https://openalex.org/W2117475509","https://openalex.org/W2120973168","https://openalex.org/W2126599826","https://openalex.org/W2136028896","https://openalex.org/W2160936694","https://openalex.org/W2161349060","https://openalex.org/W2165131017","https://openalex.org/W2166391512","https://openalex.org/W2268733724","https://openalex.org/W2728435982","https://openalex.org/W2951833906","https://openalex.org/W2979454998","https://openalex.org/W4239256582"],"related_works":["https://openalex.org/W4401325445","https://openalex.org/W2622284819","https://openalex.org/W1504394672","https://openalex.org/W4250844750","https://openalex.org/W2136028896","https://openalex.org/W2914364344","https://openalex.org/W3089381707","https://openalex.org/W1849825599","https://openalex.org/W3215936217","https://openalex.org/W4285254085"],"abstract_inverted_index":{"Previous":[0],"research":[1],"has":[2],"demonstrated":[3],"the":[4,30,58,63,71],"utility":[5],"of":[6,60,75],"clustering":[7,24,46],"in":[8],"inducing":[9],"semantic":[10],"verb":[11],"classes":[12],"from":[13],"undisambiguated":[14,78],"corpus":[15],"data.":[16,80],"We":[17],"describe":[18],"a":[19,67],"new":[20],"approach":[21],"which":[22,55],"involves":[23],"subcategorization":[25],"frame":[26],"(SCF)":[27],"distributions":[28],"using":[29],"Information":[31],"Bottleneck":[32],"and":[33,73],"nearest":[34],"neighbour":[35],"methods.":[36],"In":[37],"contrast":[38],"to":[39],"previous":[40],"work,":[41],"we":[42],"particularly":[43],"focus":[44],"on":[45,62],"polysemic":[47],"verbs.":[48],"A":[49],"novel":[50],"evaluation":[51],"scheme":[52],"is":[53],"proposed":[54],"accounts":[56],"for":[57],"effect":[59],"polysemy":[61],"clusters,":[64],"offering":[65],"us":[66],"good":[68],"insight":[69],"into":[70],"potential":[72],"limitations":[74],"semantically":[76],"classifying":[77],"SCF":[79]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}