{"id":"https://openalex.org/W2103723730","doi":"https://doi.org/10.3115/1218955.1218977","title":"Collocation translation acquisition using monolingual corpora","display_name":"Collocation translation acquisition using monolingual corpora","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2103723730","doi":"https://doi.org/10.3115/1218955.1218977","mag":"2103723730"},"language":"en","primary_location":{"id":"doi:10.3115/1218955.1218977","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1218955.1218977","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1218977&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics - ACL '04","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=1218977&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100891517","display_name":"Yajuan L\u00fc","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yajuan L\u00fc","raw_affiliation_strings":["Microsoft Research Asia, Haidian District, Beijing, China","Microsoft Research Asia, Haidian District, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Haidian District, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Haidian District, Beijing, China#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100701572","display_name":"Ming Zhou","orcid":"https://orcid.org/0000-0002-2551-2964"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Ming ZHOU","raw_affiliation_strings":["Microsoft Research Asia, Haidian District, Beijing, China","Microsoft Research Asia, Haidian District, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Haidian District, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Haidian District, Beijing, China#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":41,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"167","last_page":"es"},"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":0.9952999949455261,"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/T12353","display_name":"Lexicography and Language Studies","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/collocation","display_name":"Collocation (remote sensing)","score":0.9171651601791382},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8595775365829468},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7905164361000061},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.7701149582862854},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.7595638036727905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7130773663520813},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.658727765083313},{"id":"https://openalex.org/keywords/dependency-grammar","display_name":"Dependency grammar","score":0.5063520669937134},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.4872232973575592},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.4744119346141815},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11051809787750244}],"concepts":[{"id":"https://openalex.org/C80023036","wikidata":"https://www.wikidata.org/wiki/Q5147531","display_name":"Collocation (remote sensing)","level":2,"score":0.9171651601791382},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8595775365829468},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7905164361000061},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.7701149582862854},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.7595638036727905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7130773663520813},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.658727765083313},{"id":"https://openalex.org/C164883195","wikidata":"https://www.wikidata.org/wiki/Q674834","display_name":"Dependency grammar","level":3,"score":0.5063520669937134},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.4872232973575592},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.4744119346141815},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11051809787750244},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/1218955.1218977","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1218955.1218977","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1218977&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics - ACL '04","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.533.2648","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.533.2648","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/ACL-2004-Lu.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1218955.1218977","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1218955.1218977","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1218977&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics - ACL '04","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2103723730.pdf","grobid_xml":"https://content.openalex.org/works/W2103723730.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W62790609","https://openalex.org/W337053624","https://openalex.org/W1480519300","https://openalex.org/W1554769004","https://openalex.org/W1593045043","https://openalex.org/W1940278502","https://openalex.org/W1971002525","https://openalex.org/W2001609185","https://openalex.org/W2006969979","https://openalex.org/W2021307530","https://openalex.org/W2041232209","https://openalex.org/W2102749417","https://openalex.org/W2106022904","https://openalex.org/W2107540895","https://openalex.org/W2108869098","https://openalex.org/W2116780029","https://openalex.org/W2118669325","https://openalex.org/W2121415745","https://openalex.org/W2123282296","https://openalex.org/W2138247936","https://openalex.org/W2150071570","https://openalex.org/W2395065282","https://openalex.org/W2406316402","https://openalex.org/W2439228446","https://openalex.org/W2542591955","https://openalex.org/W4229727521","https://openalex.org/W4302780227"],"related_works":["https://openalex.org/W2251084681","https://openalex.org/W287510790","https://openalex.org/W2098784136","https://openalex.org/W3117798239","https://openalex.org/W2968543375","https://openalex.org/W2571817549","https://openalex.org/W1541975828","https://openalex.org/W2888625260","https://openalex.org/W2159336305","https://openalex.org/W3035970863"],"abstract_inverted_index":{"Collocation":[0],"translation":[1,6,55,72,99,106],"is":[2,57,74],"important":[3],"for":[4,25],"machine":[5],"and":[7,35,45,100],"many":[8],"other":[9],"NLP":[10],"tasks.":[11],"Unlike":[12],"previous":[13],"methods":[14,95],"using":[15,59],"bilingual":[16],"parallel":[17],"corpora,":[18],"this":[19],"paper":[20],"presents":[21],"a":[22,52,65],"new":[23],"method":[24],"acquiring":[26],"collocation":[27,78,105],"translations":[28,79],"by":[29],"making":[30],"use":[31],"of":[32],"monolingual":[33,82,92],"corpora":[34,47],"linguistic":[36],"knowledge.":[37],"First,":[38],"dependency":[39,49,53,66,97],"triples":[40],"are":[41],"extracted":[42],"from":[43,80],"Chinese":[44],"English":[46],"with":[48],"parsers.":[50],"Then,":[51],"triple":[54,71,98],"model":[56,73],"estimated":[58],"the":[60,90],"EM":[61],"algorithm":[62],"based":[63,94],"on":[64],"correspondence":[67],"assumption.":[68],"The":[69],"generated":[70],"used":[75],"to":[76],"extract":[77],"two":[81],"corpora.":[83],"Experiments":[84],"show":[85],"that":[86],"our":[87],"approach":[88],"outperforms":[89],"existing":[91],"corpus":[93],"in":[96,104],"achieves":[101],"promising":[102],"results":[103],"extraction.":[107]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}