{"id":"https://openalex.org/W2798720361","doi":"https://doi.org/10.18653/v1/p18-2040","title":"Improving Topic Quality by Promoting Named Entities in Topic Modeling","display_name":"Improving Topic Quality by Promoting Named Entities in Topic Modeling","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2798720361","doi":"https://doi.org/10.18653/v1/p18-2040","mag":"2798720361"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p18-2040","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-2040","pdf_url":"https://www.aclweb.org/anthology/P18-2040.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P18-2040.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052326684","display_name":"Katsiaryna Krasnashchok","orcid":"https://orcid.org/0000-0002-8152-2569"},"institutions":[{"id":"https://openalex.org/I4210129992","display_name":"Novadip (Belgium)","ror":"https://ror.org/02xc9kn92","country_code":"BE","type":"company","lineage":["https://openalex.org/I4210129992"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Katsiaryna Krasnashchok","raw_affiliation_strings":["EURA NOVA Rue Emile Francqui, 4 1435 Mont-Saint-Guibert, Belgium"],"affiliations":[{"raw_affiliation_string":"EURA NOVA Rue Emile Francqui, 4 1435 Mont-Saint-Guibert, Belgium","institution_ids":["https://openalex.org/I4210129992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064692278","display_name":"Salim Jouili","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129992","display_name":"Novadip (Belgium)","ror":"https://ror.org/02xc9kn92","country_code":"BE","type":"company","lineage":["https://openalex.org/I4210129992"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Salim Jouili","raw_affiliation_strings":["EURA NOVA Rue Emile Francqui, 4 1435 Mont-Saint-Guibert, Belgium"],"affiliations":[{"raw_affiliation_string":"EURA NOVA Rue Emile Francqui, 4 1435 Mont-Saint-Guibert, Belgium","institution_ids":["https://openalex.org/I4210129992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5052326684"],"corresponding_institution_ids":["https://openalex.org/I4210129992"],"apc_list":null,"apc_paid":null,"fwci":2.6061,"has_fulltext":true,"cited_by_count":38,"citation_normalized_percentile":{"value":0.91879531,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"247","last_page":"253"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9965999722480774,"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":0.9962000250816345,"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/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.9067676067352295},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.903718113899231},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.841998815536499},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7829856276512146},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6056539416313171},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.545752227306366},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.528663158416748},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5280424356460571},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5184618830680847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43543657660484314},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4282700717449188},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.41159144043922424},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33195990324020386},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05807635188102722}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.9067676067352295},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.903718113899231},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.841998815536499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7829856276512146},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6056539416313171},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.545752227306366},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.528663158416748},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5280424356460571},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5184618830680847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43543657660484314},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4282700717449188},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.41159144043922424},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33195990324020386},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05807635188102722},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p18-2040","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-2040","pdf_url":"https://www.aclweb.org/anthology/P18-2040.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p18-2040","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-2040","pdf_url":"https://www.aclweb.org/anthology/P18-2040.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2798720361.pdf","grobid_xml":"https://content.openalex.org/works/W2798720361.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1786797669","https://openalex.org/W1880262756","https://openalex.org/W1981231959","https://openalex.org/W1983719983","https://openalex.org/W1988680150","https://openalex.org/W2038043464","https://openalex.org/W2098401485","https://openalex.org/W2103587173","https://openalex.org/W2113533029","https://openalex.org/W2126267628","https://openalex.org/W2130339025","https://openalex.org/W2147946282","https://openalex.org/W2160170318","https://openalex.org/W2165599843","https://openalex.org/W2169401934","https://openalex.org/W2250533720","https://openalex.org/W2251582277","https://openalex.org/W2461271816","https://openalex.org/W2581611733","https://openalex.org/W2756642070","https://openalex.org/W2782303220","https://openalex.org/W2785669960","https://openalex.org/W2962842434","https://openalex.org/W2963738950","https://openalex.org/W2963956191"],"related_works":["https://openalex.org/W3099443532","https://openalex.org/W2254180092","https://openalex.org/W3204681432","https://openalex.org/W3208189550","https://openalex.org/W4308949089","https://openalex.org/W2798720361","https://openalex.org/W2287895733","https://openalex.org/W4226048468","https://openalex.org/W2370554703","https://openalex.org/W2405038964"],"abstract_inverted_index":{"News-related":[0],"content":[1,48],"has":[2,31],"been":[3],"extensively":[4],"studied":[5],"in":[6,68],"both":[7],"topic":[8,69],"modeling":[9],"research":[10],"and":[11,21,49,82],"named":[12,19,41,66],"entity":[13],"recognition.":[14],"However,":[15],"expressive":[16],"power":[17],"of":[18,28,76],"entities":[20,42,67],"their":[22,79],"potential":[23],"for":[24,46,55],"improving":[25,78],"the":[26,73],"quality":[27,75],"discovered":[29],"topics":[30],"not":[32],"received":[33],"much":[34],"attention.":[35],"In":[36],"this":[37],"paper":[38],"we":[39],"use":[40],"as":[43],"domain-specific":[44],"terms":[45],"newscentric":[47],"present":[50],"a":[51],"new":[52],"weighting":[53],"model":[54],"Latent":[56],"Dirichlet":[57],"Allocation.":[58],"Our":[59],"experimental":[60],"results":[61],"indicate":[62],"that":[63],"involving":[64],"more":[65],"descriptors":[70],"positively":[71],"influences":[72],"overall":[74],"topics,":[77],"interpretability,":[80],"specificity":[81],"diversity.":[83]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-02-04T23:10:29.248076","created_date":"2025-10-10T00:00:00"}