{"id":"https://openalex.org/W2963325132","doi":"https://doi.org/10.18653/v1/k16-1004","title":"Semi-supervised Clustering for Short Text via Deep Representation Learning","display_name":"Semi-supervised Clustering for Short Text via Deep Representation Learning","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2963325132","doi":"https://doi.org/10.18653/v1/k16-1004","mag":"2963325132"},"language":"en","primary_location":{"id":"doi:10.18653/v1/k16-1004","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k16-1004","pdf_url":"https://www.aclweb.org/anthology/K16-1004.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 20th SIGNLL Conference on Computational Natural Language Learning","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/K16-1004.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100430087","display_name":"Zhiguo Wang","orcid":"https://orcid.org/0000-0002-2412-6172"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhiguo Wang","raw_affiliation_strings":["IBM T.J. Watson Research Center Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071533156","display_name":"Haitao Mi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haitao Mi","raw_affiliation_strings":["IBM T.J. Watson Research Center Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112897636","display_name":"Abraham Ittycheriah","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abraham Ittycheriah","raw_affiliation_strings":["IBM T.J. Watson Research Center Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100430087"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":51,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"39"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9988999962806702,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.996399998664856,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8529211282730103},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.7822127938270569},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7556931972503662},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6485722064971924},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6053081750869751},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5776042342185974},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5478191375732422},{"id":"https://openalex.org/keywords/k-means-clustering","display_name":"k-means clustering","score":0.5213919281959534},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.49404075741767883},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45683854818344116},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4443928599357605},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4228472113609314},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4146694540977478},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4095120429992676}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8529211282730103},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.7822127938270569},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7556931972503662},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6485722064971924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6053081750869751},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5776042342185974},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5478191375732422},{"id":"https://openalex.org/C207968372","wikidata":"https://www.wikidata.org/wiki/Q310401","display_name":"k-means clustering","level":3,"score":0.5213919281959534},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.49404075741767883},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45683854818344116},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4443928599357605},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4228472113609314},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4146694540977478},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4095120429992676},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/k16-1004","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k16-1004","pdf_url":"https://www.aclweb.org/anthology/K16-1004.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 20th SIGNLL Conference on Computational Natural Language Learning","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/k16-1004","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k16-1004","pdf_url":"https://www.aclweb.org/anthology/K16-1004.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 20th SIGNLL Conference on Computational Natural Language Learning","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963325132.pdf","grobid_xml":"https://content.openalex.org/works/W2963325132.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1552847225","https://openalex.org/W1614298861","https://openalex.org/W1663973292","https://openalex.org/W1775434803","https://openalex.org/W1832693441","https://openalex.org/W1993691975","https://openalex.org/W2070246124","https://openalex.org/W2072240081","https://openalex.org/W2073459066","https://openalex.org/W2088314245","https://openalex.org/W2096100960","https://openalex.org/W2100495367","https://openalex.org/W2113054345","https://openalex.org/W2127097022","https://openalex.org/W2127218421","https://openalex.org/W2130556178","https://openalex.org/W2141461755","https://openalex.org/W2144499799","https://openalex.org/W2251410829","https://openalex.org/W2594639291","https://openalex.org/W2952733303","https://openalex.org/W2964121744"],"related_works":["https://openalex.org/W2952821581","https://openalex.org/W4311618633","https://openalex.org/W2185776155","https://openalex.org/W4401883448","https://openalex.org/W4379648054","https://openalex.org/W2604976738","https://openalex.org/W2113424041","https://openalex.org/W2592235592","https://openalex.org/W2904779692","https://openalex.org/W2120258591"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,13],"propose":[4],"a":[5,24,38],"semisupervised":[6],"method":[7,123],"for":[8,34],"short":[9,73],"text":[10,74,130],"clustering,":[11],"where":[12],"represent":[14],"texts":[15],"as":[16],"distributed":[17],"vectors":[18],"with":[19,57],"neural":[20,86,102],"networks,":[21],"and":[22,47,53,61,111],"use":[23],"small":[25],"amount":[26],"of":[27],"labeled":[28,59],"data":[29,60,63],"to":[30,41,75,105],"specify":[31],"our":[32,122],"intention":[33],"clustering.":[35],"We":[36],"design":[37],"novel":[39],"objective":[40,56,107],"combine":[42],"the":[43,48,55,84,90,106],"representation":[44,82],"learning":[45],"process":[46,51],"kmeans":[49],"clustering":[50,131],"together,":[52],"optimize":[54],"both":[58],"unlabeled":[62],"iteratively":[64],"until":[65],"convergence":[66],"through":[67],"three":[68],"steps:":[69],"(1)":[70],"assign":[71],"each":[72],"its":[76,81],"nearest":[77],"centroid":[78],"based":[79,93],"on":[80,94,117],"from":[83,97],"current":[85],"networks;":[87],"(2)":[88],"re-estimate":[89],"cluster":[91,95,112],"centroids":[92,110],"assignments":[96,113],"step":[98],"(1);":[99],"(3)":[100],"update":[101],"networks":[103],"according":[104],"by":[108],"keeping":[109],"fixed.":[114],"Experimental":[115],"results":[116],"four":[118],"datasets":[119],"show":[120],"that":[121],"works":[124],"significantly":[125],"better":[126],"than":[127],"several":[128],"other":[129],"methods.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}