{"id":"https://openalex.org/W2082543015","doi":"https://doi.org/10.1109/nlpke.2010.5587783","title":"Automatic filtration of multiword units","display_name":"Automatic filtration of multiword units","publication_year":2010,"publication_date":"2010-08-01","ids":{"openalex":"https://openalex.org/W2082543015","doi":"https://doi.org/10.1109/nlpke.2010.5587783","mag":"2082543015"},"language":"en","primary_location":{"id":"doi:10.1109/nlpke.2010.5587783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2010.5587783","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering(NLPKE-2010)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100414146","display_name":"Ying Liu","orcid":"https://orcid.org/0000-0002-1230-6395"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Liu","raw_affiliation_strings":["Department of Chinese Language and Literature, Tsinghua University, Beijing, China","Department of Chinese Language and Literature, Tsinghua University, Beijing, China, 100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chinese Language and Literature, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Chinese Language and Literature, Tsinghua University, Beijing, China, 100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110793934","display_name":"Zheng Tie","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Tie","raw_affiliation_strings":["Department of Chinese Language and Literature, Tsinghua University, Beijing, China","Department of Chinese Language and Literature, Tsinghua University, Beijing, China, 100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chinese Language and Literature, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Chinese Language and Literature, Tsinghua University, Beijing, China, 100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19461923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2276","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9997000098228455,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9839000105857849,"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":0.9833999872207642,"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":0.7360796928405762},{"id":"https://openalex.org/keywords/filtration","display_name":"Filtration (mathematics)","score":0.6191366910934448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5740070343017578},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"Part-of-speech tagging","score":0.5521951913833618},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5106483101844788},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.43178680539131165},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4267825484275818},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17859047651290894},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.1422346532344818},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10733893513679504}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7360796928405762},{"id":"https://openalex.org/C128489963","wikidata":"https://www.wikidata.org/wiki/Q1187724","display_name":"Filtration (mathematics)","level":2,"score":0.6191366910934448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5740070343017578},{"id":"https://openalex.org/C2780684714","wikidata":"https://www.wikidata.org/wiki/Q1271424","display_name":"Part-of-speech tagging","level":3,"score":0.5521951913833618},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5106483101844788},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.43178680539131165},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4267825484275818},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17859047651290894},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.1422346532344818},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10733893513679504}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/nlpke.2010.5587783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2010.5587783","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering(NLPKE-2010)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1498763386","https://openalex.org/W1568297139","https://openalex.org/W2038721957","https://openalex.org/W2071940869","https://openalex.org/W2077656994","https://openalex.org/W2101196694","https://openalex.org/W2119864770","https://openalex.org/W2222445509","https://openalex.org/W2361266459"],"related_works":["https://openalex.org/W2363447991","https://openalex.org/W2128096361","https://openalex.org/W2275441552","https://openalex.org/W3022465890","https://openalex.org/W2349070910","https://openalex.org/W2181804353","https://openalex.org/W2549013010","https://openalex.org/W2141346479","https://openalex.org/W2391924256","https://openalex.org/W1773803948"],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2],"how":[3],"to":[4,13],"filtrate":[5],"multiword":[6,15,23,50],"units.":[7],"We":[8],"use":[9],"normalized":[10],"expectation":[11],"(NE)":[12],"extract":[14],"unit":[16,24],"candidates":[17,25],"from":[18],"patent":[19],"corpus.":[20],"Then":[21],"the":[22,46],"are":[26],"filtrated":[27],"using":[28],"stop":[29,33,36],"words,":[30,34,37],"frequency,":[31],"first":[32],"last":[35],"and":[38],"contextual":[39],"entropy.":[40],"The":[41],"experimental":[42],"result":[43],"shows":[44],"that":[45],"precision":[47],"rate":[48],"of":[49],"units":[51],"is":[52],"improved":[53],"by":[54],"8.7%":[55],"after":[56],"filtration.":[57]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}