{"id":"https://openalex.org/W2439228446","doi":"https://doi.org/10.3115/1034678.1034730","title":"Automatic identification of non-compositional phrases","display_name":"Automatic identification of non-compositional phrases","publication_year":1999,"publication_date":"1999-01-01","ids":{"openalex":"https://openalex.org/W2439228446","doi":"https://doi.org/10.3115/1034678.1034730","mag":"2439228446"},"language":"en","primary_location":{"id":"doi:10.3115/1034678.1034730","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034730","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034730","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics  -","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034730","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110265834","display_name":"Dekang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I46247651","display_name":"University of Manitoba","ror":"https://ror.org/02gfys938","country_code":"CA","type":"education","lineage":["https://openalex.org/I46247651"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Dekang Lin","raw_affiliation_strings":["University of Manitoba, Winnipeg, Manitoba, Canada"],"affiliations":[{"raw_affiliation_string":"University of Manitoba, Winnipeg, Manitoba, Canada","institution_ids":["https://openalex.org/I46247651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5110265834"],"corresponding_institution_ids":["https://openalex.org/I46247651"],"apc_list":null,"apc_paid":null,"fwci":4.6776,"has_fulltext":true,"cited_by_count":208,"citation_normalized_percentile":{"value":0.95004678,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"317","last_page":"324"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":0.9994999766349792,"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/T12031","display_name":"Speech and dialogue systems","score":0.9926999807357788,"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/phrase","display_name":"Phrase","score":0.8583276271820068},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7748454809188843},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7706698179244995},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6816905736923218},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6319468021392822},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.62623131275177},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.5575423240661621},{"id":"https://openalex.org/keywords/composition","display_name":"Composition (language)","score":0.4282544255256653},{"id":"https://openalex.org/keywords/noun-phrase","display_name":"Noun phrase","score":0.41119006276130676},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33772552013397217},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21968698501586914}],"concepts":[{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.8583276271820068},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7748454809188843},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7706698179244995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6816905736923218},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6319468021392822},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.62623131275177},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.5575423240661621},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.4282544255256653},{"id":"https://openalex.org/C153962237","wikidata":"https://www.wikidata.org/wiki/Q1401131","display_name":"Noun phrase","level":3,"score":0.41119006276130676},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33772552013397217},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21968698501586914},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3115/1034678.1034730","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034730","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034730","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics  -","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.13.8035","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.13.8035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/P/P99/P99-1041.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.35.9092","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.35.9092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.cs.umanitoba.ca/pub/lindek/papers/noncomp.ps.gz","raw_type":"text"},{"id":"pmh:oai:acl.sr.language-archives.org:P99-1041","is_oa":false,"landing_page_url":"http://www.aclweb.org/anthology/P99-1041","pdf_url":null,"source":{"id":"https://openalex.org/S4306402137","display_name":"The COCOON platform (University of Paris)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102197404","host_organization_name":"Universit\u00e9 Paris-Sud","host_organization_lineage":["https://openalex.org/I102197404"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:americanae.aecid.es:3657138","is_oa":false,"landing_page_url":"http://americanae.aecid.es/americanae/es/registros/registro.do?tipoRegistro=MTD&idBib=3657138","pdf_url":null,"source":{"id":"https://openalex.org/S4306400786","display_name":"Americanae (AECID Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.3115/1034678.1034730","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034730","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034730","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics  -","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2439228446.pdf","grobid_xml":"https://content.openalex.org/works/W2439228446.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W128995279","https://openalex.org/W238404058","https://openalex.org/W272752870","https://openalex.org/W1480519300","https://openalex.org/W1530916949","https://openalex.org/W1595779392","https://openalex.org/W1940278502","https://openalex.org/W1940552124","https://openalex.org/W2069185229","https://openalex.org/W2102381086","https://openalex.org/W2106022904","https://openalex.org/W2109779030","https://openalex.org/W2116780029","https://openalex.org/W2123084125","https://openalex.org/W2123489126","https://openalex.org/W2158243292","https://openalex.org/W2166776180","https://openalex.org/W2950810699","https://openalex.org/W4255198209","https://openalex.org/W4388152766"],"related_works":["https://openalex.org/W2039546652","https://openalex.org/W2466816617","https://openalex.org/W1970834875","https://openalex.org/W842936808","https://openalex.org/W3174028392","https://openalex.org/W2012262991","https://openalex.org/W2000517284","https://openalex.org/W2365318811","https://openalex.org/W2136503713","https://openalex.org/W2375330620"],"abstract_inverted_index":{"Non-compositional":[0],"expressions":[1,18],"present":[2,10],"a":[3,11,24,36,62],"special":[4],"challenge":[5],"to":[6],"NLP":[7],"applications.":[8],"We":[9],"method":[12,28],"for":[13],"automatic":[14],"identification":[15],"of":[16,49,55],"non-compositional":[17],"using":[19],"their":[20],"statistical":[21],"properties":[22],"in":[23,58],"text":[25],"corpus.":[26],"Our":[27],"is":[29,38],"based":[30],"on":[31],"the":[32,46,56,59],"hypothesis":[33],"that":[34],"when":[35],"phrase":[37,60],"non-composition,":[39],"its":[40],"mutual":[41,47],"information":[42],"differs":[43],"significantly":[44],"from":[45],"informations":[48],"phrases":[50],"obtained":[51],"by":[52],"substituting":[53],"one":[54],"word":[57],"with":[61],"similar":[63],"word.":[64]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":34},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":10}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}