{"id":"https://openalex.org/W4390684394","doi":"https://doi.org/10.1162/coli_a_00506","title":"Topics in the Haystack: Enhancing Topic Quality through Corpus Expansion","display_name":"Topics in the Haystack: Enhancing Topic Quality through Corpus Expansion","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390684394","doi":"https://doi.org/10.1162/coli_a_00506"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00506","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00506","pdf_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00506/2207530/coli_a_00506.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00506/2207530/coli_a_00506.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063790800","display_name":"Anton Thielmann","orcid":"https://orcid.org/0000-0002-6768-8992"},"institutions":[{"id":"https://openalex.org/I43980791","display_name":"Clausthal University of Technology","ror":"https://ror.org/04qb8nc58","country_code":"DE","type":"education","lineage":["https://openalex.org/I43980791"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anton Thielmann","raw_affiliation_strings":["Institute of Mathematics Clausthal University of Technology. Anton.thielmann@tu-clausthal.de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Mathematics Clausthal University of Technology. Anton.thielmann@tu-clausthal.de","institution_ids":["https://openalex.org/I43980791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067506028","display_name":"Arik Reuter","orcid":"https://orcid.org/0009-0002-7837-7011"},"institutions":[{"id":"https://openalex.org/I4210120266","display_name":"Czech Academy of Sciences, Institute of Mathematics","ror":"https://ror.org/02tv1yf50","country_code":"CZ","type":"facility","lineage":["https://openalex.org/I202391551","https://openalex.org/I4210120266"]},{"id":"https://openalex.org/I43980791","display_name":"Clausthal University of Technology","ror":"https://ror.org/04qb8nc58","country_code":"DE","type":"education","lineage":["https://openalex.org/I43980791"]}],"countries":["CZ","DE"],"is_corresponding":false,"raw_author_name":"Arik Reuter","raw_affiliation_strings":["Institute of Mathematics Clausthal University of Technology. Arik.reuter@gmx.de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Mathematics Clausthal University of Technology. Arik.reuter@gmx.de","institution_ids":["https://openalex.org/I43980791","https://openalex.org/I4210120266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040137002","display_name":"Quentin Seifert","orcid":null},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Quentin Seifert","raw_affiliation_strings":["Spatial Data Science and Statistical Learning University of G\u00f6ttingen. Quentinedward.seifert@uni-goettingen.de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spatial Data Science and Statistical Learning University of G\u00f6ttingen. Quentinedward.seifert@uni-goettingen.de","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043960694","display_name":"Elisabeth Bergherr","orcid":"https://orcid.org/0000-0003-3983-9957"},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Elisabeth Bergherr","raw_affiliation_strings":["Spatial Data Science and Statistical Learning University of G\u00f6ttingen. Elisabeth.bergherr@uni-goettingen.de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spatial Data Science and Statistical Learning University of G\u00f6ttingen. Elisabeth.bergherr@uni-goettingen.de","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016630281","display_name":"Benjamin S\u00e4fken","orcid":"https://orcid.org/0000-0003-4702-3333"},"institutions":[{"id":"https://openalex.org/I4210120266","display_name":"Czech Academy of Sciences, Institute of Mathematics","ror":"https://ror.org/02tv1yf50","country_code":"CZ","type":"facility","lineage":["https://openalex.org/I202391551","https://openalex.org/I4210120266"]},{"id":"https://openalex.org/I43980791","display_name":"Clausthal University of Technology","ror":"https://ror.org/04qb8nc58","country_code":"DE","type":"education","lineage":["https://openalex.org/I43980791"]}],"countries":["CZ","DE"],"is_corresponding":false,"raw_author_name":"Benjamin S\u00e4fken","raw_affiliation_strings":["Institute of Mathematics Clausthal University of Technology. Benjamin.saefken@tu-clausthal.de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Mathematics Clausthal University of Technology. Benjamin.saefken@tu-clausthal.de","institution_ids":["https://openalex.org/I43980791","https://openalex.org/I4210120266"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5006,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.89936897,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"50","issue":"2","first_page":"619","last_page":"655"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":0.9998000264167786,"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":0.9980000257492065,"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":0.8550804257392883},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.8045167922973633},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.6915102005004883},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.685073971748352},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6447676420211792},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5654224753379822},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.5381798148155212},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.504953920841217},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5027108192443848},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.46674567461013794},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.41995736956596375},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.41315871477127075},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38981279730796814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8550804257392883},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.8045167922973633},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.6915102005004883},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.685073971748352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6447676420211792},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5654224753379822},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.5381798148155212},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.504953920841217},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5027108192443848},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.46674567461013794},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.41995736956596375},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41315871477127075},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38981279730796814},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1162/coli_a_00506","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00506","pdf_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00506/2207530/coli_a_00506.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:57f8d35c5dde40a4bb19a4ac5bf52d42","is_oa":true,"landing_page_url":"https://doaj.org/article/57f8d35c5dde40a4bb19a4ac5bf52d42","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 50, Iss 2 (2024)","raw_type":"article"},{"id":"pmh:oai:publications.goettingen-research-online.de:2/144398","is_oa":true,"landing_page_url":"https://resolver.sub.uni-goettingen.de/purl?gro-2/144398","pdf_url":null,"source":{"id":"https://openalex.org/S4306401634","display_name":"GoeScholar  The Publication Server of the Georg-August-Universit\u00e4t G\u00f6ttingen (Georg-August-Universit\u00e4t G\u00f6ttingen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210122495","host_organization_name":"Asklepios Klinik St. Georg","host_organization_lineage":["https://openalex.org/I4210122495"],"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":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00506","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00506","pdf_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00506/2207530/coli_a_00506.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4390684394.pdf"},"referenced_works_count":92,"referenced_works":["https://openalex.org/W1608124888","https://openalex.org/W1833785989","https://openalex.org/W1969486090","https://openalex.org/W1972453411","https://openalex.org/W1994041491","https://openalex.org/W2004192095","https://openalex.org/W2008915744","https://openalex.org/W2029119058","https://openalex.org/W2089358714","https://openalex.org/W2092713700","https://openalex.org/W2112050062","https://openalex.org/W2121537574","https://openalex.org/W2128925311","https://openalex.org/W2134731454","https://openalex.org/W2135505871","https://openalex.org/W2150286230","https://openalex.org/W2157006255","https://openalex.org/W2159426623","https://openalex.org/W2165533158","https://openalex.org/W2240344567","https://openalex.org/W2250533720","https://openalex.org/W2250753706","https://openalex.org/W2404506086","https://openalex.org/W2586593666","https://openalex.org/W2601243251","https://openalex.org/W2613000335","https://openalex.org/W2625714162","https://openalex.org/W2751265046","https://openalex.org/W2768113420","https://openalex.org/W2784194212","https://openalex.org/W2790740913","https://openalex.org/W2889326414","https://openalex.org/W2892379661","https://openalex.org/W2896457183","https://openalex.org/W2949169239","https://openalex.org/W2950015742","https://openalex.org/W2952478253","https://openalex.org/W2965373594","https://openalex.org/W2968713397","https://openalex.org/W2970641574","https://openalex.org/W3008374555","https://openalex.org/W3016473712","https://openalex.org/W3021299154","https://openalex.org/W3036644138","https://openalex.org/W3045464143","https://openalex.org/W3096236010","https://openalex.org/W3100651519","https://openalex.org/W3156450083","https://openalex.org/W3157512552","https://openalex.org/W3169386149","https://openalex.org/W3174519801","https://openalex.org/W3175962280","https://openalex.org/W3176380929","https://openalex.org/W3196813608","https://openalex.org/W4221074805","https://openalex.org/W4221142221","https://openalex.org/W4226497305","https://openalex.org/W4230955671","https://openalex.org/W4231510805","https://openalex.org/W4284960486","https://openalex.org/W4287100616","https://openalex.org/W4287687124","https://openalex.org/W4300672471","https://openalex.org/W4312051823","https://openalex.org/W4361193722","https://openalex.org/W4378470965","https://openalex.org/W4385574240","https://openalex.org/W4389520774","https://openalex.org/W6638697285","https://openalex.org/W6639619044","https://openalex.org/W6676519436","https://openalex.org/W6679775712","https://openalex.org/W6680343917","https://openalex.org/W6682044806","https://openalex.org/W6683240801","https://openalex.org/W6683333316","https://openalex.org/W6689880833","https://openalex.org/W6691363302","https://openalex.org/W6734688555","https://openalex.org/W6748189484","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6773815586","https://openalex.org/W6776148200","https://openalex.org/W6781923719","https://openalex.org/W6797676422","https://openalex.org/W6804781428","https://openalex.org/W6810311456","https://openalex.org/W6846751984","https://openalex.org/W6851533997","https://openalex.org/W6852591161","https://openalex.org/W6888962268"],"related_works":["https://openalex.org/W2888805565","https://openalex.org/W4312773271","https://openalex.org/W4315588616","https://openalex.org/W2769501189","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W4293863151","https://openalex.org/W3159709618","https://openalex.org/W2611137333","https://openalex.org/W3005513013"],"abstract_inverted_index":{"Abstract":[0],"Extracting":[1],"and":[2,42,57,60,108,125,147,156],"identifying":[3],"latent":[4,78],"topics":[5,79],"in":[6,14,67,93,111],"large":[7,144],"text":[8],"corpora":[9],"have":[10],"gained":[11],"increasing":[12],"importance":[13],"Natural":[15],"Language":[16],"Processing":[17],"(NLP).":[18],"Most":[19],"models,":[20,33],"whether":[21],"probabilistic":[22],"models":[23],"similar":[24],"to":[25],"Latent":[26],"Dirichlet":[27],"Allocation":[28],"(LDA)":[29],"or":[30,85],"neural":[31],"topic":[32,40,43,154],"follow":[34],"the":[35,68,94,112,131,136,165],"same":[36],"underlying":[37],"approach":[38],"of":[39,54,122,139],"interpretability":[41],"extraction.":[44],"We":[45,115,134],"propose":[46,99],"a":[47,51,143],"method":[48,141],"that":[49,80],"incorporates":[50],"deeper":[52],"understanding":[53],"both":[55],"sentence":[56],"document":[58,157],"themes,":[59],"goes":[61],"beyond":[62],"simply":[63],"analyzing":[64],"word":[65],"frequencies":[66],"data.":[69],"Through":[70],"simple":[71],"corpus":[72],"expansion,":[73],"our":[74,140],"model":[75],"can":[76],"detect":[77],"may":[81],"include":[82],"uncommon":[83],"words":[84,90,107,124],"neologisms,":[86],"as":[87,89],"well":[88],"not":[91],"present":[92,116],"documents":[95],"themselves.":[96],"Additionally,":[97],"we":[98],"several":[100],"new":[101],"evaluation":[102],"metrics":[103],"based":[104],"on":[105],"intruder":[106,123],"similarity":[109],"measures":[110],"semantic":[113],"space.":[114],"correlation":[117],"coefficients":[118],"with":[119,142,152],"human":[120],"identification":[121],"achieve":[126,148],"near-human":[127],"level":[128],"results":[129,150],"at":[130,164],"word-intrusion":[132],"task.":[133],"demonstrate":[135],"competitive":[137],"performance":[138],"benchmark":[145],"study,":[146],"superior":[149],"compared":[151],"state-of-the-art":[153],"modeling":[155],"clustering":[158],"models.":[159],"The":[160],"code":[161],"is":[162],"available":[163],"following":[166],"link:":[167],"https://github.com/AnFreTh/STREAM.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}