{"id":"https://openalex.org/W2103349583","doi":"https://doi.org/10.3115/1117794.1117820","title":"One sense per collocation and genre/topic variations","display_name":"One sense per collocation and genre/topic variations","publication_year":2000,"publication_date":"2000-01-01","ids":{"openalex":"https://openalex.org/W2103349583","doi":"https://doi.org/10.3115/1117794.1117820","mag":"2103349583"},"language":"en","primary_location":{"id":"doi:10.3115/1117794.1117820","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1117794.1117820","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1117794.1117820","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2000 Joint SIGDAT conference on Empirical methods in natural language processing and very large corpora held in conjunction with the 38th Annual Meeting of the Association for Computational Linguistics -","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/10.3115/1117794.1117820","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071033512","display_name":"David Mart\u00ednez","orcid":"https://orcid.org/0000-0002-8969-9318"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"David Martinez","raw_affiliation_strings":["University of the Basque Country, Donostia, Spain","Univ. of the Basque Country, Donostia, Spain"],"affiliations":[{"raw_affiliation_string":"University of the Basque Country, Donostia, Spain","institution_ids":["https://openalex.org/I169108374"]},{"raw_affiliation_string":"Univ. of the Basque Country, Donostia, Spain","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047151336","display_name":"Eneko Agirre","orcid":"https://orcid.org/0000-0002-0195-4899"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Eneko Agirre","raw_affiliation_strings":["University of the Basque Country, Donostia, Spain","Univ. of the Basque Country, Donostia, Spain"],"affiliations":[{"raw_affiliation_string":"University of the Basque Country, Donostia, Spain","institution_ids":["https://openalex.org/I169108374"]},{"raw_affiliation_string":"Univ. of the Basque Country, Donostia, Spain","institution_ids":["https://openalex.org/I169108374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5071033512"],"corresponding_institution_ids":["https://openalex.org/I169108374"],"apc_list":null,"apc_paid":null,"fwci":4.2436,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":{"value":0.94322672,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"13","issue":null,"first_page":"207","last_page":"215"},"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":0.9998000264167786,"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/T12031","display_name":"Speech and dialogue systems","score":0.9952999949455261,"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/collocation","display_name":"Collocation (remote sensing)","score":0.9492697715759277},{"id":"https://openalex.org/keywords/word-sense-disambiguation","display_name":"Word-sense disambiguation","score":0.8705326318740845},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7244230508804321},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6793407201766968},{"id":"https://openalex.org/keywords/sense","display_name":"Sense (electronics)","score":0.6315199732780457},{"id":"https://openalex.org/keywords/semeval","display_name":"SemEval","score":0.611098051071167},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5887219309806824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4482826292514801},{"id":"https://openalex.org/keywords/common-sense","display_name":"Common sense","score":0.41200146079063416},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4082438349723816},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06635740399360657},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.06570953130722046},{"id":"https://openalex.org/keywords/wordnet","display_name":"WordNet","score":0.06330263614654541}],"concepts":[{"id":"https://openalex.org/C80023036","wikidata":"https://www.wikidata.org/wiki/Q5147531","display_name":"Collocation (remote sensing)","level":2,"score":0.9492697715759277},{"id":"https://openalex.org/C51646954","wikidata":"https://www.wikidata.org/wiki/Q48522","display_name":"Word-sense disambiguation","level":3,"score":0.8705326318740845},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7244230508804321},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6793407201766968},{"id":"https://openalex.org/C143141573","wikidata":"https://www.wikidata.org/wiki/Q7450971","display_name":"Sense (electronics)","level":2,"score":0.6315199732780457},{"id":"https://openalex.org/C44572571","wikidata":"https://www.wikidata.org/wiki/Q7448970","display_name":"SemEval","level":3,"score":0.611098051071167},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5887219309806824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4482826292514801},{"id":"https://openalex.org/C2779814899","wikidata":"https://www.wikidata.org/wiki/Q332880","display_name":"Common sense","level":2,"score":0.41200146079063416},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4082438349723816},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06635740399360657},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.06570953130722046},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.06330263614654541},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.3115/1117794.1117820","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1117794.1117820","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1117794.1117820","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2000 Joint SIGDAT conference on Empirical methods in natural language processing and very large corpora held in conjunction with the 38th Annual Meeting of the Association for Computational Linguistics -","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1011.7681","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1011.7681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/David_Martinez14/publication/2570203_One_Sense_per_Collocation_and_GenreTopic_Variations/links/0fcfd508f21b41ba17000000.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1022.7464","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1022.7464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/David_Martinez14/publication/216591559_One_Sense_per_Collocation_and_GenreTopic_Variations/links/00b49524f80e2f27b5000000.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1032.9075","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1032.9075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/David_Martinez14/publication/2570203_One_Sense_per_Collocation_and_GenreTopic_Variations/links/0fcfd508f21b41ba17000000.pdf?origin%3Dpublication_detail","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.13.6406","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.13.6406","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/W/W00/W00-1326.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.29.5079","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.29.5079","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/dokument/Artikulu/00EMNLP.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.342.6046","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.342.6046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/cs/0010027v1.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.415.7421","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.415.7421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.jhu.edu/~yarowsky/acl2000/sigdat/martinez.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1117794.1117820","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1117794.1117820","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1117794.1117820","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2000 Joint SIGDAT conference on Empirical methods in natural language processing and very large corpora held in conjunction with the 38th Annual Meeting of the Association for Computational Linguistics -","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2103349583.pdf","grobid_xml":"https://content.openalex.org/works/W2103349583.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W152958635","https://openalex.org/W181737412","https://openalex.org/W1555805532","https://openalex.org/W1589180892","https://openalex.org/W1731244441","https://openalex.org/W1972383226","https://openalex.org/W1977182536","https://openalex.org/W2038201841","https://openalex.org/W2047620598","https://openalex.org/W2065157922","https://openalex.org/W2101210369","https://openalex.org/W2135843243","https://openalex.org/W2156202195","https://openalex.org/W2157025692","https://openalex.org/W2213505007","https://openalex.org/W2577247608","https://openalex.org/W2949109629","https://openalex.org/W2949743947","https://openalex.org/W2950121111","https://openalex.org/W2951990284","https://openalex.org/W3037715718","https://openalex.org/W4242626930","https://openalex.org/W6780672502"],"related_works":["https://openalex.org/W2101293500","https://openalex.org/W2103349583","https://openalex.org/W2384058382","https://openalex.org/W2951597351","https://openalex.org/W2000205775","https://openalex.org/W2251529656","https://openalex.org/W2324822715","https://openalex.org/W2330879361","https://openalex.org/W4287588159","https://openalex.org/W2140343536"],"abstract_inverted_index":{"This":[0,63],"paper":[1],"revisits":[2],"the":[3,20,56,65,88],"one":[4,40,53],"sense":[5,11,26,41,71,90,100],"per":[6,42],"collocation":[7,43],"hypothesis":[8,21],"using":[9],"fine-grained":[10,25],"distinctions":[12,27],"and":[13,60,109],"two":[14,81],"different":[15],"corpora.":[16,74],"We":[17,36],"show":[18,38],"that":[19,39,49,79],"is":[22],"weaker":[23],"for":[24],"(70%":[28],"vs.":[29],"99%":[30],"reported":[31],"earlier":[32],"on":[33,98,114],"2-way":[34],"ambiguities).":[35],"also":[37],"does":[44],"hold":[45],"across":[46,73],"corpora,":[47],"but":[48],"collocations":[50],"vary":[51],"from":[52],"corpus":[54],"to":[55,104],"other,":[57],"following":[58],"genre":[59,108],"topic":[61,110],"variations.":[62],"explains":[64],"low":[66],"results":[67,92],"when":[68,80],"performing":[69],"word":[70,89,99],"disambiguation":[72,91,101],"In":[75],"fact,":[76],"we":[77],"demonstrate":[78],"independent":[82],"corpora":[83],"share":[84],"a":[85],"related":[86],"genre/topic,":[87],"would":[93],"be":[94],"better.":[95],"Future":[96],"work":[97],"will":[102],"have":[103],"take":[105],"into":[106],"account":[107],"as":[111],"important":[112],"parameters":[113],"their":[115],"models.":[116]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}