{"id":"https://openalex.org/W2171190411","doi":"https://doi.org/10.1109/fskd.2011.6020036","title":"Automatic extraction and filtration of multiword units1","display_name":"Automatic extraction and filtration of multiword units1","publication_year":2011,"publication_date":"2011-07-01","ids":{"openalex":"https://openalex.org/W2171190411","doi":"https://doi.org/10.1109/fskd.2011.6020036","mag":"2171190411"},"language":"en","primary_location":{"id":"doi:10.1109/fskd.2011.6020036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2011.6020036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 Eighth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)","raw_type":"proceedings-article"},"type":"article","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/A5112116986","display_name":"Ying Liu","orcid":"https://orcid.org/0000-0003-3987-0954"},"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":true,"raw_author_name":"Ying Liu","raw_affiliation_strings":["Department of Chinese Language and Literature, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Chinese Language and Literature, Tsinghua University, Beijing, China","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"],"affiliations":[{"raw_affiliation_string":"Department of Chinese Language and Literature, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5112116986"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.4276,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74417232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"10","issue":null,"first_page":"2591","last_page":"2595"},"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/T10181","display_name":"Natural Language Processing 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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.994700014591217,"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/dice","display_name":"Dice","score":0.8835082054138184},{"id":"https://openalex.org/keywords/s\u00f8rensen\u2013dice-coefficient","display_name":"S\u00f8rensen\u2013Dice coefficient","score":0.6420395374298096},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.633336067199707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5703836679458618},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45943683385849},{"id":"https://openalex.org/keywords/filtration","display_name":"Filtration (mathematics)","score":0.4563560485839844},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4441995620727539},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2743944525718689},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.25849083065986633}],"concepts":[{"id":"https://openalex.org/C22029948","wikidata":"https://www.wikidata.org/wiki/Q45089","display_name":"Dice","level":2,"score":0.8835082054138184},{"id":"https://openalex.org/C163892561","wikidata":"https://www.wikidata.org/wiki/Q2613728","display_name":"S\u00f8rensen\u2013Dice coefficient","level":4,"score":0.6420395374298096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.633336067199707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5703836679458618},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45943683385849},{"id":"https://openalex.org/C128489963","wikidata":"https://www.wikidata.org/wiki/Q1187724","display_name":"Filtration (mathematics)","level":2,"score":0.4563560485839844},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4441995620727539},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2743944525718689},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.25849083065986633},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fskd.2011.6020036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2011.6020036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 Eighth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W272752870","https://openalex.org/W1568297139","https://openalex.org/W2023392367","https://openalex.org/W2071940869","https://openalex.org/W2077656994","https://openalex.org/W2119864770","https://openalex.org/W2222445509","https://openalex.org/W2234028104","https://openalex.org/W2361266459","https://openalex.org/W2621423192","https://openalex.org/W6739199022"],"related_works":["https://openalex.org/W3104750253","https://openalex.org/W3021239166","https://openalex.org/W4402926319","https://openalex.org/W4389060404","https://openalex.org/W2973136608","https://openalex.org/W3012828488","https://openalex.org/W4286233748","https://openalex.org/W4254054209","https://openalex.org/W4200334192","https://openalex.org/W2952835238"],"abstract_inverted_index":{"We":[0,38],"use":[1],"five":[2,43],"statistical":[3],"models":[4,44],"including":[5,97],"Dice":[6,62,74,129,140],"coefficient":[7,13],"(Dice),":[8],"\u03a6":[9],"<sup":[10,15],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[11,16],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[12,17],"(\u03a6":[14],"),":[18],"log":[19],"likelihood":[20],"ratio":[21],"(LLR),":[22],"symmetrical":[23],"conditional":[24],"probability":[25],"(SCP),":[26],"and":[27,45,58,78,110,125,144,165],"normalized":[28],"expectation(NE)":[29],"to":[30,157],"extract":[31],"multiword":[32,50,70,88,118,137,163,170],"unit":[33,51,71,89],"candidates":[34,52,72,90],"from":[35,42],"patent":[36],"corpus.":[37],"compare":[39],"the":[40,47,56,59,64,67,76,79,84,87,100,115,123,126,131,134,142,145,150,159,167],"results":[41],"find":[46],"number":[48,68,116,135],"of":[49,61,69,81,117,128,136,147,169],"using":[53,73,93,120,139],"NE":[54,121],"is":[55,63,75,83,122,130,141,149],"most":[57,124],"precision":[60,80,127,146,168],"maximal,":[65,132],"but":[66,133],"least":[77,143],"SCP":[82,148],"minimum.":[85,151],"Next":[86],"are":[91],"filtrated":[92],"these":[94],"filtration":[95,153],"strategies":[96],"stop":[98,105,108],"words,":[99,106,109],"threshold,":[101],"higher":[102],"frequency,":[103],"first":[104],"last":[107],"context":[111],"entropy.":[112],"After":[113],"filtration,":[114],"units":[119,138,164],"Each":[152],"strategy":[154],"all":[155],"help":[156],"identify":[158],"wrong":[160],"or":[161],"unreasonable":[162],"improve":[166],"units.":[171]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}