{"id":"https://openalex.org/W2559613745","doi":"https://doi.org/10.1162/tacl_a_00078","title":"Anchored Correlation Explanation: Topic Modeling with Minimal Domain Knowledge","display_name":"Anchored Correlation Explanation: Topic Modeling with Minimal Domain Knowledge","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2559613745","doi":"https://doi.org/10.1162/tacl_a_00078","mag":"2559613745"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00078","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00078","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00078","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":"preprint","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00078","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084930117","display_name":"Ryan J. Gallagher","orcid":"https://orcid.org/0000-0003-3040-4500"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I111236770","display_name":"University of Vermont","ror":"https://ror.org/0155zta11","country_code":"US","type":"education","lineage":["https://openalex.org/I111236770"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ryan J. Gallagher","raw_affiliation_strings":["Information Sciences Institute, University of Southern                         California","Vermont Complex Systems Center, Computational Story Lab,                         University of Vermont,","Vermont Complex Systems Center, Computational Story Lab,#N#                        University of Vermont,"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern                         California","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Vermont Complex Systems Center, Computational Story Lab,                         University of Vermont,","institution_ids":["https://openalex.org/I111236770"]},{"raw_affiliation_string":"Vermont Complex Systems Center, Computational Story Lab,#N#                        University of Vermont,","institution_ids":["https://openalex.org/I111236770"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033065723","display_name":"Kyle Reing","orcid":"https://orcid.org/0000-0002-2019-5293"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle Reing","raw_affiliation_strings":["Information Sciences Institute, University of Southern California,","[Information Sciences Institute, University of Southern California]"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California,","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"[Information Sciences Institute, University of Southern California]","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060074676","display_name":"David C. Kale","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Kale","raw_affiliation_strings":["Information Sciences Institute, University of Southern California,","[Information Sciences Institute, University of Southern California]"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California,","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"[Information Sciences Institute, University of Southern California]","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075920466","display_name":"Greg Ver Steeg","orcid":"https://orcid.org/0000-0002-0793-141X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Greg Ver Steeg","raw_affiliation_strings":["Information Sciences Institute, University of Southern California,","[Information Sciences Institute, University of Southern California]"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California,","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"[Information Sciences Institute, University of Southern California]","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5084930117"],"corresponding_institution_ids":["https://openalex.org/I111236770","https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.45835928,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.68154658,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"5","issue":null,"first_page":"529","last_page":"542"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T13910","display_name":"Computational and Text Analysis Methods","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9922000169754028,"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/generative-grammar","display_name":"Generative grammar","score":0.7587470412254333},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6940953731536865},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.6487041711807251},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6282737851142883},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5629795789718628},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5515376329421997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.533847451210022},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5235069394111633},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5198615193367004},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.5144262909889221},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5085562467575073},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.448998361825943},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18806129693984985}],"concepts":[{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7587470412254333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6940953731536865},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.6487041711807251},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6282737851142883},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5629795789718628},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5515376329421997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.533847451210022},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5235069394111633},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5198615193367004},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.5144262909889221},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5085562467575073},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.448998361825943},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18806129693984985},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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":5,"locations":[{"id":"doi:10.1162/tacl_a_00078","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00078","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00078","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:arXiv.org:1611.10277","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1611.10277","pdf_url":"https://arxiv.org/pdf/1611.10277","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:1ce83d56686945368ae6ab8d6fe4bdd8","is_oa":false,"landing_page_url":"https://doaj.org/article/1ce83d56686945368ae6ab8d6fe4bdd8","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 5 (2021)","raw_type":"article"},{"id":"doi:10.48550/arxiv.1611.10277","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1611.10277","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"mag:2559613745","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00078","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00078","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00078","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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2559613745.pdf","grobid_xml":"https://content.openalex.org/works/W2559613745.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W168564468","https://openalex.org/W192837634","https://openalex.org/W588062613","https://openalex.org/W1119287486","https://openalex.org/W1506246224","https://openalex.org/W1612003148","https://openalex.org/W1686946872","https://openalex.org/W1866891026","https://openalex.org/W1880262756","https://openalex.org/W1889660637","https://openalex.org/W2048330531","https://openalex.org/W2098062695","https://openalex.org/W2101234009","https://openalex.org/W2109154616","https://openalex.org/W2128521126","https://openalex.org/W2130339025","https://openalex.org/W2132827946","https://openalex.org/W2139865360","https://openalex.org/W2140124448","https://openalex.org/W2144750001","https://openalex.org/W2147152072","https://openalex.org/W2152402486","https://openalex.org/W2158085718","https://openalex.org/W2159426623","https://openalex.org/W2166851633","https://openalex.org/W2250317372","https://openalex.org/W2250533720","https://openalex.org/W2260672489","https://openalex.org/W2294709184","https://openalex.org/W2413868409","https://openalex.org/W2463552202","https://openalex.org/W2765903085","https://openalex.org/W2785356762","https://openalex.org/W2911742376","https://openalex.org/W2953096896","https://openalex.org/W2963625764","https://openalex.org/W2963747179"],"related_works":["https://openalex.org/W2963766892","https://openalex.org/W3035413108","https://openalex.org/W2751182262","https://openalex.org/W654937010","https://openalex.org/W3004665584","https://openalex.org/W2412320034","https://openalex.org/W3211787218","https://openalex.org/W3135390601","https://openalex.org/W2963007778","https://openalex.org/W2962826925","https://openalex.org/W2562573853","https://openalex.org/W3032993383","https://openalex.org/W2951706337","https://openalex.org/W2560791808","https://openalex.org/W1013235724","https://openalex.org/W2419897827","https://openalex.org/W2625387573","https://openalex.org/W2808185155","https://openalex.org/W2785769537","https://openalex.org/W2972887418"],"abstract_inverted_index":{"While":[0],"generative":[1,35,58],"models":[2,36],"such":[3],"as":[4],"Latent":[5],"Dirichlet":[6],"Allocation":[7],"(LDA)":[8],"have":[9],"proven":[10],"fruitful":[11],"in":[12,127],"topic":[13,50,99],"modeling,":[14],"they":[15],"often":[16],"require":[17],"detailed":[18],"assumptions":[19],"and":[20,60,76,101,116,134],"careful":[21],"specification":[22],"of":[23,113,137],"hyperparameters.":[24],"Such":[25],"model":[26],"complexity":[27],"issues":[28],"only":[29],"compound":[30],"when":[31],"trying":[32],"to":[33,37,49,74,103,129],"generalize":[34],"incorporate":[38],"human":[39,108],"input.":[40],"We":[41],"introduce":[42],"Correlation":[43],"Explanation":[44],"(CorEx),":[45],"an":[46,56,67],"alternative":[47],"approach":[48],"modeling":[51,82],"that":[52,120,124],"does":[53],"not":[54],"assume":[55],"underlying":[57],"model,":[59],"instead":[61],"learns":[62],"maximally":[63],"informative":[64],"topics":[65,123],"through":[66,95],"information-theoretic":[68],"framework.":[69],"This":[70],"framework":[71],"naturally":[72],"generalizes":[73],"hierarchical":[75],"semi-supervised":[77,135],"extensions":[78],"with":[79,106],"no":[80],"additional":[81],"assumptions.":[83],"In":[84],"particular,":[85],"word-level":[86],"domain":[87],"knowledge":[88],"can":[89],"be":[90,104],"flexibly":[91],"incorporated":[92],"within":[93],"CorEx":[94,121],"anchor":[96],"words,":[97],"allowing":[98],"separability":[100],"representation":[102],"promoted":[105],"minimal":[107],"intervention.":[109],"Across":[110],"a":[111],"variety":[112],"datasets,":[114],"metrics,":[115],"experiments,":[117],"we":[118],"demonstrate":[119],"produces":[122],"are":[125],"comparable":[126],"quality":[128],"those":[130],"produced":[131],"by":[132],"unsupervised":[133],"variants":[136],"LDA.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}