{"id":"https://openalex.org/W2142674468","doi":"https://doi.org/10.3115/1220175.1220295","title":"Accurate collocation extraction using a multilingual parser","display_name":"Accurate collocation extraction using a multilingual parser","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2142674468","doi":"https://doi.org/10.3115/1220175.1220295","mag":"2142674468"},"language":"en","primary_location":{"id":"doi:10.3115/1220175.1220295","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220295","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220295","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220295","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004650353","display_name":"Violeta Seretan","orcid":"https://orcid.org/0000-0002-9199-9467"},"institutions":[{"id":"https://openalex.org/I114457229","display_name":"University of Geneva","ror":"https://ror.org/01swzsf04","country_code":"CH","type":"education","lineage":["https://openalex.org/I114457229"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Violeta Seretan","raw_affiliation_strings":["University of Geneva, Geneva","University of Geneva , Geneva"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Geneva, Geneva","institution_ids":["https://openalex.org/I114457229"]},{"raw_affiliation_string":"University of Geneva , Geneva","institution_ids":["https://openalex.org/I114457229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071104145","display_name":"\u00c9ric Wehrli","orcid":null},"institutions":[{"id":"https://openalex.org/I114457229","display_name":"University of Geneva","ror":"https://ror.org/01swzsf04","country_code":"CH","type":"education","lineage":["https://openalex.org/I114457229"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Eric Wehrli","raw_affiliation_strings":["University of Geneva, Geneva","University of Geneva , Geneva"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Geneva, Geneva","institution_ids":["https://openalex.org/I114457229"]},{"raw_affiliation_string":"University of Geneva , Geneva","institution_ids":["https://openalex.org/I114457229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114457229"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":56,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"953","last_page":"960"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T13629","display_name":"Text Readability and Simplification","score":0.9991000294685364,"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":0.9958999752998352,"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":0.8610150814056396},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.8284942507743835},{"id":"https://openalex.org/keywords/collocation","display_name":"Collocation (remote sensing)","score":0.7965256571769714},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6850980520248413},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6439041495323181},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.5466232895851135},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4477074146270752},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.44477176666259766},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1323986053466797}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8610150814056396},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8284942507743835},{"id":"https://openalex.org/C80023036","wikidata":"https://www.wikidata.org/wiki/Q5147531","display_name":"Collocation (remote sensing)","level":2,"score":0.7965256571769714},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6850980520248413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6439041495323181},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.5466232895851135},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4477074146270752},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.44477176666259766},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1323986053466797},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3115/1220175.1220295","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220295","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220295","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06","raw_type":"proceedings-article"},{"id":"pmh:oai:unige.ch:aou:unige:85145","is_oa":true,"landing_page_url":"https://archive-ouverte.unige.ch/unige:85145","pdf_url":null,"source":{"id":"https://openalex.org/S4306402259","display_name":"Archive ouverte UNIGE (University of Geneva)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114457229","host_organization_name":"University of Geneva","host_organization_lineage":["https://openalex.org/I114457229"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the ACL, (2006) p. 953-960","raw_type":"ConferencePaper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.143.8360","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.143.8360","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/P06/P06-1120.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.549.9503","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.549.9503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mt-archive.info/Coling-ACL-2006-Seretan.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.88.6312","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.88.6312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.latl.unige.ch/personal/vseretan/publ/COLING-ACL2006_VS_EW.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1220175.1220295","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220295","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220295","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2142674468.pdf","grobid_xml":"https://content.openalex.org/works/W2142674468.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W62790609","https://openalex.org/W272752870","https://openalex.org/W1498763386","https://openalex.org/W1566813831","https://openalex.org/W1574901103","https://openalex.org/W1592073433","https://openalex.org/W1940278502","https://openalex.org/W1976395441","https://openalex.org/W2001609185","https://openalex.org/W2038128141","https://openalex.org/W2038423395","https://openalex.org/W2042085493","https://openalex.org/W2044070623","https://openalex.org/W2080902366","https://openalex.org/W2101196694","https://openalex.org/W2116780029","https://openalex.org/W2120429080","https://openalex.org/W2121479142","https://openalex.org/W2168820179","https://openalex.org/W4388152814"],"related_works":["https://openalex.org/W2370840338","https://openalex.org/W2388641108","https://openalex.org/W2368317224","https://openalex.org/W2370651559","https://openalex.org/W2390901981","https://openalex.org/W2383177152","https://openalex.org/W3000893075","https://openalex.org/W2349694428","https://openalex.org/W2384630579","https://openalex.org/W2358919722"],"abstract_inverted_index":{"This":[0],"paper":[1],"focuses":[2],"on":[3,45],"the":[4,56],"use":[5],"of":[6,9,43],"advanced":[7],"techniques":[8],"text":[10],"analysis":[11],"as":[12],"support":[13],"for":[14,29],"collocation":[15],"extraction.":[16],"A":[17],"hybrid":[18],"system":[19],"is":[20,59],"presented":[21],"that":[22],"combines":[23],"statistical":[24],"methods":[25],"and":[26,38],"multilingual":[27],"parsing":[28,47],"detecting":[30],"accurate":[31],"collocational":[32],"information":[33],"from":[34],"English,":[35],"French,":[36],"Spanish":[37],"Italian":[39],"corpora.":[40],"The":[41],"advantage":[42],"relying":[44],"full":[46],"over":[48],"using":[49],"a":[50,67],"traditional":[51],"window":[52],"method":[53],"(which":[54],"ignores":[55],"syntactic":[57],"information)":[58],"first":[60],"theoretically":[61],"motivated,":[62],"then":[63],"empirically":[64],"validated":[65],"by":[66],"comparative":[68],"evaluation":[69],"experiment.":[70]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}