{"id":"https://openalex.org/W2739862013","doi":"https://doi.org/10.18653/v1/p17-2062","title":"Efficient Extraction of Pseudo-Parallel Sentences from Raw Monolingual Data Using Word Embeddings","display_name":"Efficient Extraction of Pseudo-Parallel Sentences from Raw Monolingual Data Using Word Embeddings","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2739862013","doi":"https://doi.org/10.18653/v1/p17-2062","mag":"2739862013"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p17-2062","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-2062","pdf_url":"https://www.aclweb.org/anthology/P17-2062.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P17-2062.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101488996","display_name":"Benjamin Marie","orcid":"https://orcid.org/0000-0002-5228-2762"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Benjamin Marie","raw_affiliation_strings":["National Institute of Information and Communications Technology 3-5 Hikaridai, Seika-cho, Souraku-gun, Kyoto, 619-0289, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology 3-5 Hikaridai, Seika-cho, Souraku-gun, Kyoto, 619-0289, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101988321","display_name":"Atsushi Fujita","orcid":"https://orcid.org/0000-0003-3799-8428"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Fujita","raw_affiliation_strings":["National Institute of Information and Communications Technology 3-5 Hikaridai, Seika-cho, Souraku-gun, Kyoto, 619-0289, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology 3-5 Hikaridai, Seika-cho, Souraku-gun, Kyoto, 619-0289, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101488996"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":2.1453,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90363334,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"392","last_page":"398"},"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/T13629","display_name":"Text Readability and Simplification","score":0.9961000084877014,"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":0.8694090247154236},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6917375326156616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.684905469417572},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6528757810592651},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.650280773639679},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6107346415519714},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5949077606201172},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5825914740562439},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5555503964424133},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4753180146217346},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4565252363681793},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4152058959007263},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07861784100532532}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8694090247154236},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6917375326156616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.684905469417572},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6528757810592651},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.650280773639679},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6107346415519714},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5949077606201172},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5825914740562439},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5555503964424133},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4753180146217346},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4565252363681793},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4152058959007263},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07861784100532532},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p17-2062","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-2062","pdf_url":"https://www.aclweb.org/anthology/P17-2062.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p17-2062","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-2062","pdf_url":"https://www.aclweb.org/anthology/P17-2062.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2739862013.pdf","grobid_xml":"https://content.openalex.org/works/W2739862013.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2000026602","https://openalex.org/W2065565011","https://openalex.org/W2101105183","https://openalex.org/W2104103102","https://openalex.org/W2107695330","https://openalex.org/W2115613106","https://openalex.org/W2126725946","https://openalex.org/W2131744502","https://openalex.org/W2141068210","https://openalex.org/W2144600658","https://openalex.org/W2153579005","https://openalex.org/W2166098990","https://openalex.org/W2320039153","https://openalex.org/W2431681589","https://openalex.org/W2508069829","https://openalex.org/W2515741950","https://openalex.org/W2567571499","https://openalex.org/W2574026469","https://openalex.org/W2588710172","https://openalex.org/W2595715041","https://openalex.org/W2949547296","https://openalex.org/W2962776659","https://openalex.org/W2963002901","https://openalex.org/W2963915291","https://openalex.org/W3166956191","https://openalex.org/W3204406378","https://openalex.org/W4238317531","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W3080655457","https://openalex.org/W2756978580","https://openalex.org/W4297577100","https://openalex.org/W3166286441","https://openalex.org/W3214142563","https://openalex.org/W3136267388","https://openalex.org/W3186065094","https://openalex.org/W4287263085","https://openalex.org/W3093803318","https://openalex.org/W3204418343"],"abstract_inverted_index":{"We":[0,48],"propose":[1],"a":[2,10,40,61],"new":[3],"method":[4,23],"for":[5,55],"extracting":[6],"pseudo-parallel":[7],"sentences":[8],"from":[9,70],"pair":[11],"of":[12,34],"large":[13],"monolingual":[14,72],"corpora,":[15],"without":[16],"relying":[17],"on":[18,65],"any":[19],"document-level":[20],"information.":[21],"Our":[22],"first":[24],"exploits":[25],"word":[26],"embeddings":[27],"in":[28,52],"order":[29],"to":[30,42],"efficiently":[31],"evaluate":[32],"trillions":[33],"candidate":[35],"sentence":[36,67],"pairs":[37,68],"and":[38],"then":[39],"classifier":[41],"find":[43],"the":[44,66],"most":[45],"reliable":[46],"ones.":[47],"report":[49],"significant":[50],"improvements":[51],"domain":[53],"adaptation":[54],"statistical":[56],"machine":[57],"translation":[58,62],"when":[59],"using":[60],"model":[63],"trained":[64],"extracted":[69],"in-domain":[71],"corpora.":[73]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}