{"id":"https://openalex.org/W2741268430","doi":"https://doi.org/10.18653/v1/w17-2510","title":"zNLP: Identifying Parallel Sentences in Chinese-English Comparable Corpora","display_name":"zNLP: Identifying Parallel Sentences in Chinese-English Comparable Corpora","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2741268430","doi":"https://doi.org/10.18653/v1/w17-2510","mag":"2741268430"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-2510","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2510","pdf_url":"https://www.aclweb.org/anthology/W17-2510.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th Workshop on Building and Using Comparable Corpora","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-2510.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100459168","display_name":"Zheng Zhang","orcid":"https://orcid.org/0000-0003-1470-6998"},"institutions":[{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I4210144804","display_name":"Laboratoire de Recherche en Informatique","ror":"https://ror.org/04e3ktk27","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210144804","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Zheng Zhang","raw_affiliation_strings":["LIMSI, CNRS, Universit\u00e9 Paris-Saclay Orsay, France","Universit\u00e9 Paris-Saclay Orsay, France","LRI, Univ. Paris-Sud, CNRS,"],"affiliations":[{"raw_affiliation_string":"LIMSI, CNRS, Universit\u00e9 Paris-Saclay Orsay, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I1294671590","https://openalex.org/I4210115485"]},{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay Orsay, France","institution_ids":["https://openalex.org/I277688954"]},{"raw_affiliation_string":"LRI, Univ. Paris-Sud, CNRS,","institution_ids":["https://openalex.org/I4210144804","https://openalex.org/I102197404","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090195478","display_name":"Pierre Zweigenbaum","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210090571","display_name":"Institut des Sciences des Plantes de Paris Saclay","ror":"https://ror.org/00ajjta07","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I277688954","https://openalex.org/I277688954","https://openalex.org/I4210088668","https://openalex.org/I4210090571","https://openalex.org/I88467170"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pierre Zweigenbaum","raw_affiliation_strings":["LIMSI, CNRS, Universit Paris-Saclay Orsay, France","LIMSI, CNRS, Universit\u00e9 Paris-Saclay Orsay, France"],"affiliations":[{"raw_affiliation_string":"LIMSI, CNRS, Universit Paris-Saclay Orsay, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I4210090571","https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LIMSI, CNRS, Universit\u00e9 Paris-Saclay Orsay, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I1294671590","https://openalex.org/I4210115485"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100459168"],"corresponding_institution_ids":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4210115485","https://openalex.org/I4210144804"],"apc_list":null,"apc_paid":null,"fwci":1.2431,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.85105001,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"55"},"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":0.9998999834060669,"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/T12031","display_name":"Speech and dialogue systems","score":0.992900013923645,"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":0.7573225498199463},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6540387272834778},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5107043385505676},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38904911279678345}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573225498199463},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6540387272834778},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5107043385505676},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38904911279678345}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w17-2510","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2510","pdf_url":"https://www.aclweb.org/anthology/W17-2510.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th Workshop on Building and Using Comparable Corpora","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-2510","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2510","pdf_url":"https://www.aclweb.org/anthology/W17-2510.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th Workshop on Building and Using Comparable Corpora","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6399999856948853,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2741268430.pdf","grobid_xml":"https://content.openalex.org/works/W2741268430.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W8895266","https://openalex.org/W22168010","https://openalex.org/W108460122","https://openalex.org/W2105673178","https://openalex.org/W2107695330","https://openalex.org/W2111329418","https://openalex.org/W2118989374","https://openalex.org/W2170240176","https://openalex.org/W2265389615","https://openalex.org/W2580557349","https://openalex.org/W2963012544","https://openalex.org/W4322490533"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W3204019825"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,7,30,51,63],"zNLP":[4],"system":[5,13],"for":[6],"BUCC":[8],"2017":[9],"shared":[10],"task.":[11],"Our":[12],"identifies":[14],"parallel":[15,48],"sentence":[16],"pairs":[17],"in":[18],"Chinese-English":[19],"comparable":[20],"corpora":[21],"by":[22,40],"translating":[23],"word-by-word":[24],"Chinese":[25],"sentences":[26,37,49],"into":[27],"English,":[28],"using":[29,41],"search":[31],"engine":[32],"Solr":[33],"to":[34,45],"select":[35],"near-parallel":[36],"and":[38],"then":[39],"an":[42,56],"SVM":[43],"classifier":[44],"identify":[46],"true":[47],"from":[50],"previous":[52],"results.":[53],"It":[54],"obtains":[55],"F1-score":[57],"of":[58],"45%":[59],"(resp.":[60],"43%)":[61],"on":[62],"test":[64],"(training)":[65],"set.":[66]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2026-03-07T13:37:22.277990","created_date":"2025-10-10T00:00:00"}
