{"id":"https://openalex.org/W2126788554","doi":"https://doi.org/10.1109/nlpke.2010.5587827","title":"Data selection for statistical machine translation","display_name":"Data selection for statistical machine translation","publication_year":2010,"publication_date":"2010-08-01","ids":{"openalex":"https://openalex.org/W2126788554","doi":"https://doi.org/10.1109/nlpke.2010.5587827","mag":"2126788554"},"language":"en","primary_location":{"id":"doi:10.1109/nlpke.2010.5587827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2010.5587827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering(NLPKE-2010)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100346747","display_name":"Peng Liu","orcid":"https://orcid.org/0000-0001-6568-1335"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Liu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101815945","display_name":"Zhou Yu","orcid":"https://orcid.org/0000-0002-1524-5890"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhou","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015785439","display_name":"Chengqing Zong","orcid":"https://orcid.org/0000-0002-9864-3818"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengqing Zong","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8174,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72932893,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9995999932289124,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9879999756813049,"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/machine-translation","display_name":"Machine translation","score":0.8530594110488892},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8357682228088379},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.725914716720581},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.656726598739624},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6400793194770813},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6365519165992737},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5972280502319336},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.503438413143158},{"id":"https://openalex.org/keywords/machine-translation-software-usability","display_name":"Machine translation software usability","score":0.4442424178123474}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8530594110488892},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8357682228088379},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.725914716720581},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.656726598739624},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6400793194770813},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6365519165992737},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5972280502319336},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.503438413143158},{"id":"https://openalex.org/C148526163","wikidata":"https://www.wikidata.org/wiki/Q6723733","display_name":"Machine translation software usability","level":4,"score":0.4442424178123474},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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":1,"locations":[{"id":"doi:10.1109/nlpke.2010.5587827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2010.5587827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering(NLPKE-2010)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1586104099","https://openalex.org/W2047295649","https://openalex.org/W2099111195","https://openalex.org/W2101105183","https://openalex.org/W2116042738","https://openalex.org/W2136477195","https://openalex.org/W2146113428","https://openalex.org/W2146574666","https://openalex.org/W2153653739","https://openalex.org/W2178619104","https://openalex.org/W2399188371","https://openalex.org/W6635214705","https://openalex.org/W6685708572","https://openalex.org/W6712654473","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2566847733","https://openalex.org/W2122287718","https://openalex.org/W3204448004","https://openalex.org/W2587602790","https://openalex.org/W2740094425","https://openalex.org/W193726211","https://openalex.org/W2010336863","https://openalex.org/W3036784334","https://openalex.org/W2251549520","https://openalex.org/W3214198970"],"abstract_inverted_index":{"The":[0,61,72],"bilingual":[1],"language":[2],"corpus":[3,51,55],"has":[4],"a":[5,12,80],"great":[6],"effect":[7],"on":[8,57,68],"the":[9,29,40,49,53,58,69],"performance":[10,82],"of":[11],"statistical":[13],"machine":[14],"translation":[15,62],"system.":[16],"More":[17],"data":[18,26],"will":[19],"lead":[20],"to":[21,38],"better":[22],"performance.":[23],"However,":[24],"more":[25,45],"also":[27],"increase":[28],"computational":[30],"load.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35,77],"propose":[36],"methods":[37],"estimate":[39],"sentence":[41,59],"weight":[42],"and":[43,52,66],"select":[44],"informative":[46],"sentences":[47],"from":[48],"training":[50],"development":[54],"based":[56],"weight.":[60],"system":[63],"is":[64],"built":[65],"tuned":[67],"compact":[70],"corpus.":[71],"experimental":[73],"results":[74],"show":[75],"that":[76],"can":[78],"obtain":[79],"competitive":[81],"with":[83],"much":[84],"less":[85],"data.":[86]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
