{"id":"https://openalex.org/W2109154149","doi":"https://doi.org/10.3115/1218955.1219035","title":"Learning word senses with feature selection and order identification capabilities","display_name":"Learning word senses with feature selection and order identification capabilities","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2109154149","doi":"https://doi.org/10.3115/1218955.1219035","mag":"2109154149"},"language":"en","primary_location":{"id":"doi:10.3115/1218955.1219035","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1218955.1219035","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1218955.1219035","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics - ACL '04","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1218955.1219035","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033269202","display_name":"Zheng-Yu Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zheng-Yu Niu","raw_affiliation_strings":["Institute for Infocomm Research, Singapore","Inst. for Infocomm Res., Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Inst. for Infocomm Res., Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101801149","display_name":"Donghong Ji","orcid":"https://orcid.org/0000-0003-4020-983X"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dong-Hong Ji","raw_affiliation_strings":["Institute for Infocomm Research, Singapore","Inst. for Infocomm Res., Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Inst. for Infocomm Res., Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109209523","display_name":"Chew\u2010Lim Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chew-Lim Tan","raw_affiliation_strings":["National University of Singapore, Singapore","Nat. Univ. of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Nat. Univ. of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6615,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67232354,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"629","last_page":"es"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9958000183105469,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9958000183105469,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.994700014591217,"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":0.9918000102043152,"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/word","display_name":"Word (group theory)","score":0.7191517949104309},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7009871602058411},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6721825003623962},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6455376744270325},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.615503191947937},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6065928936004639},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5586644411087036},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5547074675559998},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.549565315246582},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5360856652259827},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.44893771409988403},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.435764342546463},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.42494070529937744},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.41824668645858765},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19897747039794922},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06106376647949219}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7191517949104309},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7009871602058411},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6721825003623962},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6455376744270325},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.615503191947937},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6065928936004639},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5586644411087036},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5547074675559998},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.549565315246582},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5360856652259827},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.44893771409988403},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.435764342546463},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.42494070529937744},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.41824668645858765},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19897747039794922},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06106376647949219},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/1218955.1219035","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1218955.1219035","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1218955.1219035","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics - ACL '04","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/1218955.1219035","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1218955.1219035","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1218955.1219035","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics - ACL '04","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2109154149.pdf","grobid_xml":"https://content.openalex.org/works/W2109154149.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1486097837","https://openalex.org/W1544729927","https://openalex.org/W1546317785","https://openalex.org/W1555805532","https://openalex.org/W1581499779","https://openalex.org/W1676314349","https://openalex.org/W1731244441","https://openalex.org/W1890873505","https://openalex.org/W1959178355","https://openalex.org/W1981276685","https://openalex.org/W2000951787","https://openalex.org/W2014915963","https://openalex.org/W2026858230","https://openalex.org/W2049633694","https://openalex.org/W2050712820","https://openalex.org/W2054658115","https://openalex.org/W2060542593","https://openalex.org/W2130337399","https://openalex.org/W2137572914","https://openalex.org/W2140259275","https://openalex.org/W2146261447","https://openalex.org/W2147830002","https://openalex.org/W2153922613","https://openalex.org/W2951421399"],"related_works":["https://openalex.org/W2807251790","https://openalex.org/W1569283511","https://openalex.org/W2799406489","https://openalex.org/W2380784125","https://openalex.org/W2049792449","https://openalex.org/W4236193183","https://openalex.org/W3004057759","https://openalex.org/W2889085215","https://openalex.org/W2914806737","https://openalex.org/W2053866214"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,54],"unsupervised":[4,55],"word":[5,14],"sense":[6],"learning":[7],"algorithm,":[8],"which":[9,97],"induces":[10],"senses":[11],"of":[12,23,29],"target":[13],"by":[15,43],"grouping":[16],"its":[17],"occurrences":[18],"into":[19],"a":[20,45],"\"natural\"":[21],"number":[22,100],"clusters":[24],"based":[25],"on":[26],"the":[27],"similarity":[28],"their":[30],"contexts.":[31],"For":[32],"removing":[33],"noisy":[34],"words":[35],"in":[36,53],"feature":[37,39,83],"set,":[38],"selection":[40],"is":[41],"conducted":[42],"optimizing":[44],"cluster":[46,69,72,99],"validation":[47],"criterion":[48,64],"subject":[49],"to":[50,67,101],"some":[51],"constraint":[52],"manner.":[56],"Gaussian":[57],"mixture":[58],"model":[59,86],"and":[60,71,90],"Minimum":[61],"Description":[62],"Length":[63],"are":[65],"used":[66],"estimate":[68,85],"structure":[70],"number.":[73],"Experimental":[74],"results":[75],"show":[76],"that":[77],"our":[78],"algorithm":[79,96],"can":[80],"find":[81],"important":[82],"subset,":[84],"order":[87],"(cluster":[88],"number)":[89],"achieve":[91],"better":[92],"performance":[93],"than":[94],"another":[95],"requires":[98],"be":[102],"provided.":[103]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}