{"id":"https://openalex.org/W2123020907","doi":"https://doi.org/10.1162/coli_a_00196","title":"Improved Estimation of Entropy for Evaluation of Word Sense Induction","display_name":"Improved Estimation of Entropy for Evaluation of Word Sense Induction","publication_year":2014,"publication_date":"2014-03-28","ids":{"openalex":"https://openalex.org/W2123020907","doi":"https://doi.org/10.1162/coli_a_00196","mag":"2123020907"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00196","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00196","pdf_url":"https://direct.mit.edu/coli/article-pdf/40/3/671/1803273/coli_a_00196.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://direct.mit.edu/coli/article-pdf/40/3/671/1803273/coli_a_00196.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100318915","display_name":"Linlin Li","orcid":"https://orcid.org/0000-0002-6387-6013"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210135422","display_name":"Microsoft (Norway)","ror":"https://ror.org/03jtz4s80","country_code":"NO","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210135422"]}],"countries":["NO","US"],"is_corresponding":false,"raw_author_name":"Linlin Li","raw_affiliation_strings":["Microsoft Development Center Norway","Microsoft Development Center Norway#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Development Center Norway","institution_ids":["https://openalex.org/I4210135422"]},{"raw_affiliation_string":"Microsoft Development Center Norway#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086717154","display_name":"Ivan Titov","orcid":"https://orcid.org/0000-0002-2583-1893"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ivan Titov","raw_affiliation_strings":["University of Amsterdam","University of Amsterdam#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"University of Amsterdam#N#","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010144873","display_name":"Caroline Sporleder","orcid":"https://orcid.org/0000-0002-5912-7028"},"institutions":[{"id":"https://openalex.org/I89864525","display_name":"Universit\u00e4t Trier","ror":"https://ror.org/02778hg05","country_code":"DE","type":"education","lineage":["https://openalex.org/I89864525"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Caroline Sporleder","raw_affiliation_strings":["Trier University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Trier University","institution_ids":["https://openalex.org/I89864525"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9689,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.85094296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"40","issue":"3","first_page":"671","last_page":"685"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9976000189781189,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9976000189781189,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.995199978351593,"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":0.9934999942779541,"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/estimator","display_name":"Estimator","score":0.823022186756134},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6589382886886597},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.6240805387496948},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5718331336975098},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.5649256110191345},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5255899429321289},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.5149338841438293},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44765153527259827},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4313846230506897},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.38883399963378906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3116127848625183},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2763345241546631}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.823022186756134},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6589382886886597},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.6240805387496948},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5718331336975098},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5649256110191345},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5255899429321289},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.5149338841438293},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44765153527259827},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4313846230506897},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.38883399963378906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3116127848625183},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2763345241546631},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1162/coli_a_00196","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00196","pdf_url":"https://direct.mit.edu/coli/article-pdf/40/3/671/1803273/coli_a_00196.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:dare.uva.nl:openaire/e7afa55b-6d54-41f6-a9d3-ec31df67f435","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/improved-estimation-of-entropy-for-evaluation-of-word-sense-induction(e7afa55b-6d54-41f6-a9d3-ec31df67f435).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Li, L, Titov, I & Sporleder, C 2014, 'Improved Estimation of Entropy for Evaluation of Word Sense Induction', Computational Linguistics, vol. 40, no. 3, pp. 671-685. https://doi.org/10.1162/COLI_a_00196","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/e7afa55b-6d54-41f6-a9d3-ec31df67f435","is_oa":true,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/improved-estimation-of-entropy-for-evaluation-of-word-sense-induction(e7afa55b-6d54-41f6-a9d3-ec31df67f435).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Li, L, Titov, I & Sporleder, C 2014, 'Improved Estimation of Entropy for Evaluation of Word Sense Induction', Computational Linguistics, vol. 40, no. 3, pp. 671-685. https://doi.org/10.1162/COLI_a_00196","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.685.3056","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.685.3056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aclweb.org/anthology/J/J14/J14-3007.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.699.6083","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.699.6083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ivan-titov.org/papers/clj14.pdf","raw_type":"text"},{"id":"pmh:oai:dare.uva.nl:publications/e7afa55b-6d54-41f6-a9d3-ec31df67f435","is_oa":false,"landing_page_url":"http://dare.uva.nl/personal/pure/en/publications/improved-estimation-of-entropy-for-evaluation-of-word-sense-induction(e7afa55b-6d54-41f6-a9d3-ec31df67f435).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:doaj.org/article:389da9af86a047f5ba4fa72a1c68d4ac","is_oa":false,"landing_page_url":"https://doaj.org/article/389da9af86a047f5ba4fa72a1c68d4ac","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 40, Iss 3 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00196","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00196","pdf_url":"https://direct.mit.edu/coli/article-pdf/40/3/671/1803273/coli_a_00196.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320323322","display_name":"Universit\u00e4t des Saarlandes","ror":"https://ror.org/01jdpyv68"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2123020907.pdf","grobid_xml":"https://content.openalex.org/works/W2123020907.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W70010159","https://openalex.org/W126722120","https://openalex.org/W1551268210","https://openalex.org/W1570448133","https://openalex.org/W1974976142","https://openalex.org/W1975084891","https://openalex.org/W2000163531","https://openalex.org/W2009952327","https://openalex.org/W2018891628","https://openalex.org/W2040820014","https://openalex.org/W2058223376","https://openalex.org/W2066680326","https://openalex.org/W2072240081","https://openalex.org/W2076237237","https://openalex.org/W2085786299","https://openalex.org/W2098345921","https://openalex.org/W2101985079","https://openalex.org/W2109584604","https://openalex.org/W2114771311","https://openalex.org/W2128822763","https://openalex.org/W2130337399","https://openalex.org/W2138615112","https://openalex.org/W2157305458","https://openalex.org/W2291181759","https://openalex.org/W2611972942","https://openalex.org/W2963673689","https://openalex.org/W2966207845","https://openalex.org/W4241850027","https://openalex.org/W4251958315","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2047973478","https://openalex.org/W4295532600","https://openalex.org/W2063823869","https://openalex.org/W2067569035","https://openalex.org/W2090985514","https://openalex.org/W4293088233","https://openalex.org/W2496077116","https://openalex.org/W3041490575","https://openalex.org/W2970690932","https://openalex.org/W4321135767"],"abstract_inverted_index":{"Information-theoretic":[0],"measures":[1,20,59],"are":[2,37],"among":[3,45],"the":[4,26,29,35,41,48,53,58,64,74,85,101,116],"most":[5],"standard":[6,30,102],"techniques":[7],"for":[8],"evaluation":[9,89,103,133],"of":[10,25,34,50,66,87,109,111,134],"clustering":[11],"methods":[12],"including":[13],"word":[14,113],"sense":[15,94],"induction":[16],"(WSI)":[17],"systems.":[18,136],"Such":[19],"rely":[21],"on":[22,132],"sample-based":[23],"estimates":[24,33],"entropy.":[27],"However,":[28],"maximum":[31],"likelihood":[32],"entropy":[36,122],"heavily":[38],"biased":[39],"with":[40],"bias":[42],"dependent":[43],"on,":[44],"other":[46],"things,":[47],"number":[49,65,95,108],"clusters":[51,67],"and":[52,61,73,100,124,131],"sample":[54,75],"size.":[55],"This":[56,81],"makes":[57],"unreliable":[60],"unfair":[62],"when":[63],"produced":[68],"by":[69],"different":[70],"systems":[71],"vary":[72],"size":[76],"is":[77],"not":[78,98],"exceedingly":[79],"large.":[80],"corresponds":[82],"exactly":[83],"to":[84,114],"setting":[86],"WSI":[88,135],"where":[90],"a":[91,106],"ground-truth":[92],"cluster":[93],"arguably":[96],"does":[97],"exist":[99],"scenarios":[104],"use":[105],"small":[107],"instances":[110],"each":[112],"compute":[115],"score.":[117],"We":[118],"describe":[119],"more":[120],"accurate":[121],"estimators":[123],"analyze":[125],"their":[126],"performance":[127],"both":[128],"in":[129],"simulations":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}