{"id":"https://openalex.org/W2251894099","doi":"https://doi.org/10.3115/v1/w15-0906","title":"Clustering-based Approach to Multiword Expression Extraction and Ranking","display_name":"Clustering-based Approach to Multiword Expression Extraction and Ranking","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2251894099","doi":"https://doi.org/10.3115/v1/w15-0906","mag":"2251894099"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w15-0906","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w15-0906","pdf_url":"https://www.aclweb.org/anthology/W15-0906.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 11th Workshop on Multiword Expressions","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W15-0906.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012311258","display_name":"Elena Tutubalina","orcid":"https://orcid.org/0000-0001-7936-0284"},"institutions":[{"id":"https://openalex.org/I21203515","display_name":"Kazan Federal University","ror":"https://ror.org/05256ym39","country_code":"RU","type":"education","lineage":["https://openalex.org/I21203515"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Elena Tutubalina","raw_affiliation_strings":["Higher Institute for Information Technology and Information Systems Kazan Federal University Kazan, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Higher Institute for Information Technology and Information Systems Kazan Federal University Kazan, Russia","institution_ids":["https://openalex.org/I21203515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5012311258"],"corresponding_institution_ids":["https://openalex.org/I21203515"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.125,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"43"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9972000122070312,"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":0.9911999702453613,"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/ranking","display_name":"Ranking (information retrieval)","score":0.8270152807235718},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7966223955154419},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7670795917510986},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6787756681442261},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5620051622390747},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.48981973528862},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.48715898394584656},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4589563012123108},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4429360330104828},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4141336679458618},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3465648293495178},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3320584297180176},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11668139696121216}],"concepts":[{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.8270152807235718},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7966223955154419},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7670795917510986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6787756681442261},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5620051622390747},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.48981973528862},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.48715898394584656},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4589563012123108},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4429360330104828},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4141336679458618},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3465648293495178},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3320584297180176},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11668139696121216},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/v1/w15-0906","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w15-0906","pdf_url":"https://www.aclweb.org/anthology/W15-0906.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 11th Workshop on Multiword Expressions","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/v1/w15-0906","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w15-0906","pdf_url":"https://www.aclweb.org/anthology/W15-0906.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 11th Workshop on Multiword Expressions","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"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/W2251894099.pdf","grobid_xml":"https://content.openalex.org/works/W2251894099.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W178414959","https://openalex.org/W938539187","https://openalex.org/W1498763386","https://openalex.org/W1523813253","https://openalex.org/W1525289242","https://openalex.org/W1537747159","https://openalex.org/W1574901103","https://openalex.org/W1981036316","https://openalex.org/W1986848965","https://openalex.org/W2011430131","https://openalex.org/W2023722231","https://openalex.org/W2030903088","https://openalex.org/W2041186695","https://openalex.org/W2064580901","https://openalex.org/W2096217913","https://openalex.org/W2118522559","https://openalex.org/W2127776561","https://openalex.org/W2134796504","https://openalex.org/W2154507487","https://openalex.org/W2165979968","https://openalex.org/W2167329753","https://openalex.org/W2168820179","https://openalex.org/W2250421663","https://openalex.org/W2250965176","https://openalex.org/W2610179052","https://openalex.org/W2803437449","https://openalex.org/W6656473211","https://openalex.org/W6677525176","https://openalex.org/W6682709971","https://openalex.org/W6723123931"],"related_works":["https://openalex.org/W2188500270","https://openalex.org/W2303858293","https://openalex.org/W4298130764","https://openalex.org/W2915512527","https://openalex.org/W2804364458","https://openalex.org/W51364034","https://openalex.org/W2793336762","https://openalex.org/W2091548507","https://openalex.org/W2132641928","https://openalex.org/W4310225030"],"abstract_inverted_index":{"We":[0,27],"present":[1],"a":[2,19,55,65],"domain-independent":[3],"clusteringbased":[4],"approach":[5],"for":[6,45,60],"automatic":[7],"extraction":[8],"of":[9,33,67,76,82],"multiword":[10],"expressions":[11],"(MWEs).":[12],"The":[13],"method":[14],"combines":[15],"statistical":[16,87],"information":[17],"from":[18,24],"general-purpose":[20],"corpus":[21],"and":[22,39,85],"texts":[23],"Wikipedia":[25],"articles.":[26],"incorporate":[28],"association":[29,68],"measures":[30,69],"via":[31],"dimensions":[32],"data":[34],"points":[35],"to":[36,54],"cluster":[37],"MWEs":[38,77],"then":[40],"compute":[41],"the":[42,50,74],"ranking":[43,75],"score":[44],"each":[46],"MWE":[47],"based":[48],"on":[49],"closest":[51],"exemplar":[52],"assigned":[53],"cluster.":[56],"Evaluation":[57],"results,":[58],"achieved":[59],"two":[61],"languages,":[62],"show":[63],"that":[64],"combination":[66],"gives":[70],"an":[71],"improvement":[72],"in":[73],"compared":[78],"with":[79],"simple":[80],"counts":[81],"cooccurrence":[83],"frequencies":[84],"purely":[86],"measures.":[88]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}