{"id":"https://openalex.org/W2739844977","doi":"https://doi.org/10.18653/v1/p17-1169","title":"Determining Gains Acquired from Word Embedding Quantitatively Using Discrete Distribution Clustering","display_name":"Determining Gains Acquired from Word Embedding Quantitatively Using Discrete Distribution Clustering","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2739844977","doi":"https://doi.org/10.18653/v1/p17-1169","mag":"2739844977"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p17-1169","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-1169","pdf_url":"https://www.aclweb.org/anthology/P17-1169.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P17-1169.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031373536","display_name":"Jianbo Ye","orcid":"https://orcid.org/0000-0003-4612-6429"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianbo Ye","raw_affiliation_strings":["The Pennsylvania State University, University Park, Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, Pennsylvania","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101698007","display_name":"Yanran Li","orcid":"https://orcid.org/0000-0002-6454-263X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yanran Li","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101973484","display_name":"Zhaohui Wu","orcid":"https://orcid.org/0000-0002-4319-3645"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaohui Wu","raw_affiliation_strings":["The Pennsylvania State University, University Park, Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, Pennsylvania","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100687159","display_name":"James Z. Wang","orcid":"https://orcid.org/0000-0003-4379-4173"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Z. Wang","raw_affiliation_strings":["The Pennsylvania State University, University Park, Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, Pennsylvania","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100408983","display_name":"Wenjie Li","orcid":"https://orcid.org/0000-0002-7360-8864"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wenjie Li","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100648219","display_name":"Jia Li","orcid":"https://orcid.org/0000-0001-8842-1042"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jia Li","raw_affiliation_strings":["The Pennsylvania State University, University Park, Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, Pennsylvania","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.969,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.80495961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1847","last_page":"1856"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/cluster-analysis","display_name":"Cluster analysis","score":0.8046574592590332},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.7952194213867188},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7769910097122192},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7504759430885315},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6464536786079407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5920109748840332},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.591249942779541},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.562028169631958},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46291592717170715},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3323186933994293},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.194656640291214}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8046574592590332},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.7952194213867188},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7769910097122192},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7504759430885315},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6464536786079407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5920109748840332},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.591249942779541},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.562028169631958},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46291592717170715},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3323186933994293},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.194656640291214},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/p17-1169","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-1169","pdf_url":"https://www.aclweb.org/anthology/P17-1169.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/77461","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/77461","pdf_url":null,"source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.18653/v1/p17-1169","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-1169","pdf_url":"https://www.aclweb.org/anthology/P17-1169.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G346262037","display_name":null,"funder_award_id":"DMS-1521092","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4276857174","display_name":"Statistical Learning for Image Annotation","funder_award_id":"1521092","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4556787103","display_name":"MRI:    Acquistion of A Scalable Instrument for Discovery through Computing","funder_award_id":"0821527","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6713216772","display_name":"EAGER-DynamicData: Generative Statistical Modeling for Dynamic and Distributed Data","funder_award_id":"1462230","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6778350887","display_name":"XSEDE: eXtreme Science and Engineering Discovery Environment","funder_award_id":"1053575","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320322598","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98"},{"id":"https://openalex.org/F4320337392","display_name":"Division of Electrical, Communications and Cyber Systems","ror":"https://ror.org/01krpsy48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2739844977.pdf","grobid_xml":"https://content.openalex.org/works/W2739844977.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W658020064","https://openalex.org/W1585160083","https://openalex.org/W1629559917","https://openalex.org/W1880262756","https://openalex.org/W1902027874","https://openalex.org/W1968333723","https://openalex.org/W1988772356","https://openalex.org/W2013029404","https://openalex.org/W2033403400","https://openalex.org/W2036996178","https://openalex.org/W2039682702","https://openalex.org/W2078667299","https://openalex.org/W2087544865","https://openalex.org/W2094963775","https://openalex.org/W2099982145","https://openalex.org/W2125483582","https://openalex.org/W2131744502","https://openalex.org/W2138615112","https://openalex.org/W2141599568","https://openalex.org/W2144211451","https://openalex.org/W2147152072","https://openalex.org/W2150695437","https://openalex.org/W2153579005","https://openalex.org/W2154872931","https://openalex.org/W2156036190","https://openalex.org/W2156718197","https://openalex.org/W2162833336","https://openalex.org/W2165599843","https://openalex.org/W2169658215","https://openalex.org/W2171852577","https://openalex.org/W2250539671","https://openalex.org/W2251013587","https://openalex.org/W2556873163","https://openalex.org/W2949547296","https://openalex.org/W2953057288","https://openalex.org/W2963995333","https://openalex.org/W4231510805","https://openalex.org/W4244030505","https://openalex.org/W4246180809","https://openalex.org/W4285719527","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W1795405792","https://openalex.org/W2899601636","https://openalex.org/W4254379378","https://openalex.org/W947140380","https://openalex.org/W4206655101","https://openalex.org/W52853789","https://openalex.org/W4286432911","https://openalex.org/W2911655849","https://openalex.org/W4230884544","https://openalex.org/W4245453790"],"abstract_inverted_index":{"Word":[0],"embeddings":[1],"have":[2,20],"become":[3],"widelyused":[4],"in":[5,77],"document":[6,46],"analysis.":[7],"While":[8],"a":[9,44,55,78,95],"large":[10],"number":[11],"of":[12,97],"models":[13],"for":[14,58],"mapping":[15],"words":[16],"to":[17,87],"vector":[18],"spaces":[19],"been":[21],"developed,":[22],"it":[23],"remains":[24],"undetermined":[25],"how":[26],"much":[27],"net":[28],"gain":[29],"can":[30],"be":[31],"achieved":[32],"over":[33],"traditional":[34],"approaches":[35],"based":[36],"on":[37,94],"bag-of-words.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42],"propose":[43],"new":[45,82],"clustering":[47,59,83],"approach":[48],"by":[49],"combining":[50],"any":[51],"word":[52],"embedding":[53],"with":[54],"state-of-the-art":[56],"algorithm":[57],"empirical":[60],"distributions.":[61],"By":[62],"using":[63],"the":[64,69],"Wasserstein":[65],"distance":[66],"between":[67],"distributions,":[68],"word-to-word":[70],"semantic":[71],"relationship":[72],"is":[73,85],"taken":[74],"into":[75],"account":[76],"principled":[79],"way.":[80],"The":[81],"method":[84],"easy":[86],"use":[88],"and":[89],"consistently":[90],"outperforms":[91],"other":[92],"methods":[93],"variety":[96],"data":[98],"sets.":[99]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":6}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}