{"id":"https://openalex.org/W2178725228","doi":"https://doi.org/10.1162/tacl_a_00140","title":"Improving Topic Models with Latent Feature Word Representations","display_name":"Improving Topic Models with Latent Feature Word Representations","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2178725228","doi":"https://doi.org/10.1162/tacl_a_00140","mag":"2178725228"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00140","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00140","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00140","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00140","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063933953","display_name":"Dat Quoc Nguyen","orcid":"https://orcid.org/0000-0001-8214-2878"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Dat Quoc Nguyen","raw_affiliation_strings":["Department of Computing, Macquarie University, Sydney, Australia,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, Macquarie University, Sydney, Australia,","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071084510","display_name":"Richard Billingsley","orcid":null},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Richard Billingsley","raw_affiliation_strings":["Department of Computing, Macquarie University, Sydney, Australia,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, Macquarie University, Sydney, Australia,","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021845515","display_name":"Lan Du","orcid":"https://orcid.org/0000-0002-9925-0223"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Lan Du","raw_affiliation_strings":["Department of Computing, Macquarie University, Sydney, Australia,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, Macquarie University, Sydney, Australia,","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034461489","display_name":"Mark Johnson","orcid":"https://orcid.org/0000-0003-4809-8441"},"institutions":[{"id":"https://openalex.org/I1308548392","display_name":"Santa Fe Institute","ror":"https://ror.org/01arysc35","country_code":"US","type":"funder","lineage":["https://openalex.org/I1308548392"]},{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU","US"],"is_corresponding":true,"raw_author_name":"Mark Johnson","raw_affiliation_strings":["Department of Computing, Macquarie University, Sydney,                         Australia","Santa Fe Institute, Santa Fe, New Mexico, USA,","Department of Computing, Macquarie University, Sydney,\n Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, Macquarie University, Sydney,                         Australia","institution_ids":["https://openalex.org/I99043593"]},{"raw_affiliation_string":"Santa Fe Institute, Santa Fe, New Mexico, USA,","institution_ids":["https://openalex.org/I1308548392"]},{"raw_affiliation_string":"Department of Computing, Macquarie University, Sydney,\n Australia","institution_ids":["https://openalex.org/I99043593"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021845515","https://openalex.org/A5034461489","https://openalex.org/A5063933953","https://openalex.org/A5071084510"],"corresponding_institution_ids":["https://openalex.org/I1308548392","https://openalex.org/I99043593"],"apc_list":null,"apc_paid":null,"fwci":37.3954,"has_fulltext":true,"cited_by_count":321,"citation_normalized_percentile":{"value":0.99771043,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"3","issue":null,"first_page":"299","last_page":"313"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9987000226974487,"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":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.8529075384140015},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.7872167229652405},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.7796390652656555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6739130020141602},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6701109409332275},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.626944899559021},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6250094771385193},{"id":"https://openalex.org/keywords/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.5725568532943726},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5422540307044983},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5203494429588318},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.47764909267425537},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.43394234776496887},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.41912686824798584},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.41314947605133057},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33611756563186646},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14446327090263367},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.12145474553108215}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8529075384140015},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.7872167229652405},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.7796390652656555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6739130020141602},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6701109409332275},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.626944899559021},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6250094771385193},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.5725568532943726},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5422540307044983},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5203494429588318},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.47764909267425537},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.43394234776496887},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.41912686824798584},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.41314947605133057},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33611756563186646},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14446327090263367},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.12145474553108215},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":2,"locations":[{"id":"doi:10.1162/tacl_a_00140","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00140","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00140","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b3479df2a716477b931d5ee076c04bdd","is_oa":false,"landing_page_url":"https://doaj.org/article/b3479df2a716477b931d5ee076c04bdd","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":"Transactions of the Association for Computational Linguistics, Vol 3 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00140","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00140","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00140","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2178725228.pdf","grobid_xml":"https://content.openalex.org/works/W2178725228.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W22861983","https://openalex.org/W65194033","https://openalex.org/W130710483","https://openalex.org/W157541337","https://openalex.org/W1506806321","https://openalex.org/W1512098439","https://openalex.org/W1516111018","https://openalex.org/W1532325895","https://openalex.org/W1714665356","https://openalex.org/W1853745982","https://openalex.org/W1880262756","https://openalex.org/W1977830790","https://openalex.org/W1978400666","https://openalex.org/W1981617416","https://openalex.org/W2001082470","https://openalex.org/W2004192095","https://openalex.org/W2051434435","https://openalex.org/W2061922307","https://openalex.org/W2063904635","https://openalex.org/W2076219102","https://openalex.org/W2087743880","https://openalex.org/W2098401485","https://openalex.org/W2100002341","https://openalex.org/W2106316877","https://openalex.org/W2113378307","https://openalex.org/W2117130368","https://openalex.org/W2122683976","https://openalex.org/W2130324521","https://openalex.org/W2130339025","https://openalex.org/W2130428211","https://openalex.org/W2133280805","https://openalex.org/W2133990480","https://openalex.org/W2144508908","https://openalex.org/W2145768976","https://openalex.org/W2146341620","https://openalex.org/W2147152072","https://openalex.org/W2147946282","https://openalex.org/W2153579005","https://openalex.org/W2159426623","https://openalex.org/W2163131995","https://openalex.org/W2165279024","https://openalex.org/W2168084958","https://openalex.org/W2168332560","https://openalex.org/W2169821025","https://openalex.org/W2174706414","https://openalex.org/W2177979027","https://openalex.org/W2197590357","https://openalex.org/W2238728730","https://openalex.org/W2250533720","https://openalex.org/W2250539671","https://openalex.org/W2491306663","https://openalex.org/W2964291985","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2921491680","https://openalex.org/W2251863249","https://openalex.org/W4291700620","https://openalex.org/W2132052677","https://openalex.org/W3159709618","https://openalex.org/W4214866631","https://openalex.org/W2110027950","https://openalex.org/W4309228610","https://openalex.org/W3046324450","https://openalex.org/W4294597112"],"abstract_inverted_index":{"Probabilistic":[0],"topic":[1,40,83],"models":[2,41,78],"are":[3],"widely":[4],"used":[5,22],"to":[6,23,55],"discover":[7],"latent":[8,14,44],"topics":[9],"in":[10,27],"document":[11,85,88],"collections,":[12],"while":[13],"feature":[15,45],"vector":[16,46],"representations":[17,47],"of":[18,48],"words":[19,49],"have":[20],"been":[21],"obtain":[24],"high":[25],"performance":[26],"many":[28],"NLP":[29],"tasks.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34],"extend":[35],"two":[36],"different":[37],"Dirichlet":[38],"multinomial":[39],"by":[42,69],"incorporating":[43],"trained":[50],"on":[51,61,82,92],"very":[52],"large":[53],"corpora":[54],"improve":[56],"the":[57,73],"word-topic":[58],"mapping":[59],"learnt":[60],"a":[62],"smaller":[63],"corpus.":[64],"Experimental":[65],"results":[66],"show":[67],"that":[68],"using":[70],"information":[71],"from":[72],"external":[74],"corpora,":[75],"our":[76],"new":[77],"produce":[79],"significant":[80],"improvements":[81],"coherence,":[84],"clustering":[86],"and":[87],"classification":[89],"tasks,":[90],"especially":[91],"datasets":[93],"with":[94],"few":[95],"or":[96],"short":[97],"documents.":[98]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":28},{"year":2021,"cited_by_count":52},{"year":2020,"cited_by_count":60},{"year":2019,"cited_by_count":45},{"year":2018,"cited_by_count":38},{"year":2017,"cited_by_count":32},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}