{"id":"https://openalex.org/W2515339322","doi":"https://doi.org/10.18653/v1/w16-1806","title":"Accounting ngrams and multi-word terms can improve topic models","display_name":"Accounting ngrams and multi-word terms can improve topic models","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2515339322","doi":"https://doi.org/10.18653/v1/w16-1806","mag":"2515339322"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w16-1806","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-1806","pdf_url":"https://www.aclweb.org/anthology/W16-1806.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 12th Workshop on Multiword Expressions","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W16-1806.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035524100","display_name":"Michael Nokel","orcid":null},"institutions":[{"id":"https://openalex.org/I58957048","display_name":"Yandex (Russia)","ror":"https://ror.org/04dbch786","country_code":"RU","type":"company","lineage":["https://openalex.org/I58957048"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Michael Nokel","raw_affiliation_strings":["Yandex, Moscow, Russian Federation"],"affiliations":[{"raw_affiliation_string":"Yandex, Moscow, Russian Federation","institution_ids":["https://openalex.org/I58957048"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003446912","display_name":"Natalia Loukachevitch","orcid":"https://orcid.org/0000-0002-1883-4121"},"institutions":[{"id":"https://openalex.org/I19880235","display_name":"Lomonosov Moscow State University","ror":"https://ror.org/010pmpe69","country_code":"RU","type":"education","lineage":["https://openalex.org/I19880235"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Natalia Loukachevitch","raw_affiliation_strings":["Lomonosov Moscow State University, Moscow, Russian Federation"],"affiliations":[{"raw_affiliation_string":"Lomonosov Moscow State University, Moscow, Russian Federation","institution_ids":["https://openalex.org/I19880235"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5035524100"],"corresponding_institution_ids":["https://openalex.org/I58957048"],"apc_list":null,"apc_paid":null,"fwci":4.4437,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.95109174,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"44","last_page":"49"},"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/T13083","display_name":"Advanced Text Analysis Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7273303866386414},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5951495170593262},{"id":"https://openalex.org/keywords/accounting","display_name":"Accounting","score":0.47756725549697876},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46988868713378906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34410542249679565},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20295488834381104},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.06901499629020691}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7273303866386414},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5951495170593262},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.47756725549697876},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46988868713378906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34410542249679565},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20295488834381104},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.06901499629020691},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w16-1806","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-1806","pdf_url":"https://www.aclweb.org/anthology/W16-1806.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 12th Workshop on Multiword Expressions","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w16-1806","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-1806","pdf_url":"https://www.aclweb.org/anthology/W16-1806.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 12th Workshop on Multiword Expressions","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321079","display_name":"Russian Foundation for Basic Research","ror":"https://ror.org/02mh1ke95"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2515339322.pdf","grobid_xml":"https://content.openalex.org/works/W2515339322.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1880262756","https://openalex.org/W1981231959","https://openalex.org/W1984251878","https://openalex.org/W2016196732","https://openalex.org/W2031203571","https://openalex.org/W2075858744","https://openalex.org/W2094951132","https://openalex.org/W2097394335","https://openalex.org/W2104210067","https://openalex.org/W2107743791","https://openalex.org/W2130339025","https://openalex.org/W2131563376","https://openalex.org/W2145768976","https://openalex.org/W2147946282","https://openalex.org/W2158085718","https://openalex.org/W2159426623","https://openalex.org/W2166753626","https://openalex.org/W2169606435","https://openalex.org/W2171319841","https://openalex.org/W2234028104","https://openalex.org/W2296641297","https://openalex.org/W2619770322","https://openalex.org/W4231510805","https://openalex.org/W4233135949"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655","https://openalex.org/W2359140296"],"abstract_inverted_index":{"The":[0,60],"paper":[1],"presents":[2],"an":[3],"empirical":[4],"study":[5],"of":[6,52,62],"integrating":[7,63],"ngrams":[8,56,64],"and":[9,20,39,65,76],"multi-word":[10],"terms":[11,67],"into":[12,57],"topic":[13,58],"models,":[14],"while":[15],"maintaining":[16],"similarities":[17],"between":[18],"them":[19],"words":[21],"based":[22],"on":[23,69],"their":[24],"component":[25],"structure.":[26],"First,":[27],"we":[28,42],"adapt":[29],"the":[30,34,50,53,84],"PLSA-SIM":[31],"algorithm":[32,46],"to":[33],"more":[35],"widespread":[36],"LDA":[37],"model":[38],"ngrams.":[40],"Then":[41],"propose":[43],"a":[44,79],"novel":[45],"LDA-ITER":[47],"that":[48],"allows":[49],"incorporation":[51],"most":[54],"suitable":[55],"models.":[59],"experiments":[61],"multiword":[66],"conducted":[68],"five":[70],"text":[71],"collections":[72],"in":[73,82],"different":[74],"languages":[75],"domains":[77],"demonstrate":[78],"significant":[80],"improvement":[81],"all":[83],"metrics":[85],"under":[86],"consideration.":[87]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4}],"updated_date":"2026-03-24T08:02:53.985720","created_date":"2025-10-10T00:00:00"}