{"id":"https://openalex.org/W2077332795","doi":"https://doi.org/10.1145/2036264.2036280","title":"Two-Word Collocation Extraction Using Monolingual Word Alignment Method","display_name":"Two-Word Collocation Extraction Using Monolingual Word Alignment Method","publication_year":2011,"publication_date":"2011-10-01","ids":{"openalex":"https://openalex.org/W2077332795","doi":"https://doi.org/10.1145/2036264.2036280","mag":"2077332795"},"language":"en","primary_location":{"id":"doi:10.1145/2036264.2036280","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2036264.2036280","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-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/A5090058238","display_name":"Zhanyi Liu","orcid":"https://orcid.org/0009-0006-2431-9587"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhanyi Liu","raw_affiliation_strings":["Harbin Institute of Technology Baidu"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology Baidu","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386394","display_name":"Haifeng Wang","orcid":"https://orcid.org/0000-0002-0672-7468"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Wang","raw_affiliation_strings":["Baidu"],"affiliations":[{"raw_affiliation_string":"Baidu","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100677198","display_name":"Hua Wu","orcid":"https://orcid.org/0000-0002-5687-7800"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Wu","raw_affiliation_strings":["Baidu"],"affiliations":[{"raw_affiliation_string":"Baidu","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["Harbin Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5090058238"],"corresponding_institution_ids":["https://openalex.org/I204983213","https://openalex.org/I98301712"],"apc_list":null,"apc_paid":null,"fwci":0.8552,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79737668,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"3","issue":"1","first_page":"1","last_page":"29"},"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/T13629","display_name":"Text Readability and Simplification","score":0.9925000071525574,"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":0.8568359613418579},{"id":"https://openalex.org/keywords/collocation","display_name":"Collocation (remote sensing)","score":0.7803125381469727},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7612791061401367},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7172225713729858},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6615020632743835},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5389441251754761},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4519221782684326},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3621451258659363},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2006860077381134}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8568359613418579},{"id":"https://openalex.org/C80023036","wikidata":"https://www.wikidata.org/wiki/Q5147531","display_name":"Collocation (remote sensing)","level":2,"score":0.7803125381469727},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7612791061401367},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7172225713729858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6615020632743835},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5389441251754761},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4519221782684326},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3621451258659363},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2006860077381134},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2036264.2036280","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2036264.2036280","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.800000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W80619934","https://openalex.org/W1566813831","https://openalex.org/W1568140279","https://openalex.org/W1574901103","https://openalex.org/W1592073433","https://openalex.org/W1593045043","https://openalex.org/W1596902275","https://openalex.org/W1597896561","https://openalex.org/W1669953352","https://openalex.org/W1940278502","https://openalex.org/W1973923101","https://openalex.org/W1975879668","https://openalex.org/W1994560811","https://openalex.org/W1998719346","https://openalex.org/W2002205242","https://openalex.org/W2005550043","https://openalex.org/W2006969979","https://openalex.org/W2015693178","https://openalex.org/W2044070623","https://openalex.org/W2044157185","https://openalex.org/W2050034861","https://openalex.org/W2053696726","https://openalex.org/W2065925951","https://openalex.org/W2096217913","https://openalex.org/W2101210369","https://openalex.org/W2103407879","https://openalex.org/W2108869098","https://openalex.org/W2114210953","https://openalex.org/W2114930830","https://openalex.org/W2116780029","https://openalex.org/W2142674468","https://openalex.org/W2164777277","https://openalex.org/W2166089232","https://openalex.org/W2250591306","https://openalex.org/W2341250624","https://openalex.org/W2511006972","https://openalex.org/W2546541005","https://openalex.org/W2593831809","https://openalex.org/W2991446475","https://openalex.org/W2997757304","https://openalex.org/W2998215494","https://openalex.org/W2998237634","https://openalex.org/W6649719734"],"related_works":["https://openalex.org/W2370840338","https://openalex.org/W2388641108","https://openalex.org/W2368317224","https://openalex.org/W2370651559","https://openalex.org/W2383177152","https://openalex.org/W3000893075","https://openalex.org/W2349694428","https://openalex.org/W2384630579","https://openalex.org/W2358919722","https://openalex.org/W2362350383"],"abstract_inverted_index":{"Statistical":[0],"bilingual":[1,18,50],"word":[2,19,51,77,90,130],"alignment":[3,20,78,97],"has":[4],"been":[5],"well":[6],"studied":[7],"in":[8,39,45,49,64],"the":[9,17,34,37,54,75,88,96,179],"field":[10],"of":[11,70,151,176],"machine":[12],"translation.":[13],"This":[14],"article":[15],"adapts":[16],"algorithm":[21,79],"into":[22],"a":[23,40,61,133,154,173],"monolingual":[24,30,55,76],"scenario":[25],"to":[26,43,59,82,95,118,125,144],"extract":[27,126,167],"collocations":[28,127,168],"from":[29,128],"corpus,":[31,63],"based":[32],"on":[33,111,153,159,178],"fact":[35],"that":[36,121],"words":[38],"collocation":[41],"tend":[42],"co-occur":[44],"similar":[46],"contexts":[47],"as":[48,106],"alignment.":[52],"First,":[53],"corpus":[56,156],"is":[57,80],"replicated":[58],"generate":[60],"parallel":[62],"which":[65],"each":[66],"sentence":[67],"pair":[68],"consists":[69],"two":[71],"identical":[72],"sentences.":[73],"Next,":[74],"employed":[81],"align":[83],"potentially":[84],"collocated":[85],"words.":[86],"Finally,":[87],"aligned":[89],"pairs":[91,131],"are":[92,104],"ranked":[93],"according":[94],"scores":[98,103],"and":[99,113,141,157],"candidates":[100],"with":[101,169],"higher":[102,139,174],"extracted":[105],"collocations.":[107,185],"We":[108],"conducted":[109],"experiments":[110],"Chinese":[112,155,184],"English":[114,161],"corpora":[115],"respectively.":[116],"Compared":[117],"previous":[119],"approaches":[120],"use":[122],"association":[123],"measures":[124],"co-occurrence":[129],"within":[132],"given":[134],"window,":[135],"our":[136,147],"method":[137,148],"achieves":[138,149],"precision":[140,175],"recall.":[142],"According":[143],"human":[145],"evaluation,":[146],"precisions":[150],"62%":[152],"64%":[158],"an":[160],"corpus.":[162],"In":[163],"particular,":[164],"we":[165],"can":[166],"longer":[170],"spans,":[171],"achieving":[172],"83%":[177],"long-span":[180],"(>":[181],"6":[182],"words)":[183]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}