{"id":"https://openalex.org/W3118265739","doi":"https://doi.org/10.18653/v1/2020.wmt-1.112","title":"Volctrans Parallel Corpus Filtering System for WMT 2020","display_name":"Volctrans Parallel Corpus Filtering System for WMT 2020","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3118265739","doi":"https://doi.org/10.18653/v1/2020.wmt-1.112","mag":"3118265739"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.wmt-1.112","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.112","pdf_url":"https://aclanthology.org/2020.wmt-1.112.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 Fifth Conference on Machine Translation","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2020.wmt-1.112.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023594937","display_name":"Runxin Xu","orcid":"https://orcid.org/0000-0002-3876-2284"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runxin Xu","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002332644","display_name":"Zhuo Zhi","orcid":"https://orcid.org/0000-0002-0517-1525"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuo Zhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057370662","display_name":"Jun Cao","orcid":"https://orcid.org/0000-0002-5634-3008"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101693713","display_name":"Mingxuan Wang","orcid":"https://orcid.org/0009-0008-3376-6762"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingxuan Wang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100440407","display_name":"Lei Li","orcid":"https://orcid.org/0000-0003-3095-9776"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Li","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]}],"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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"985","last_page":"990"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9948999881744385,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9315999746322632,"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":0.8186751008033752},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7054383754730225},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6326617002487183},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6255171895027161},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.572772741317749},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5016961097717285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46847406029701233},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.46451395750045776},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39180606603622437},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33682170510292053},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07921841740608215}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8186751008033752},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7054383754730225},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6326617002487183},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6255171895027161},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.572772741317749},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5016961097717285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46847406029701233},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.46451395750045776},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39180606603622437},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33682170510292053},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07921841740608215},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2020.wmt-1.112","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.112","pdf_url":"https://aclanthology.org/2020.wmt-1.112.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 Fifth Conference on Machine Translation","raw_type":"proceedings-article"},{"id":"mag:3118265739","is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/2020.wmt-1.112.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418267","display_name":"Empirical Methods in Natural Language Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Empirical Methods in Natural Language Processing","raw_type":null}],"best_oa_location":{"id":"doi:10.18653/v1/2020.wmt-1.112","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.112","pdf_url":"https://aclanthology.org/2020.wmt-1.112.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 Fifth Conference on Machine Translation","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.5400000214576721,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3118265739.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3119453866","https://openalex.org/W2902319873","https://openalex.org/W3120459072","https://openalex.org/W2953063840","https://openalex.org/W2903061071","https://openalex.org/W2902009742","https://openalex.org/W2798389157","https://openalex.org/W3119770416","https://openalex.org/W3118643801","https://openalex.org/W2031811896","https://openalex.org/W2561179958","https://openalex.org/W2902608666","https://openalex.org/W2462968517","https://openalex.org/W2970916202","https://openalex.org/W2917066545","https://openalex.org/W2518455057","https://openalex.org/W2963929887","https://openalex.org/W2126061668","https://openalex.org/W2035718809","https://openalex.org/W2949375376"],"abstract_inverted_index":{"In":[0,84],"this":[1],"paper,":[2],"we":[3],"describe":[4],"our":[5],"submissions":[6,100],"to":[7,26,79],"the":[8,24,34,66,70,85,102],"WMT20":[9],"shared":[10],"task":[11,22],"on":[12,65,112],"parallel":[13,29,82],"corpus":[14],"filtering":[15],"and":[16,38,60,97,106,110],"alignment":[17,68],"for":[18,108],"low-resource":[19],"conditions.":[20,115],"The":[21],"requires":[23],"participants":[25],"align":[27],"potential":[28],"sentence":[30],"pairs":[31,44],"out":[32],"of":[33,53],"given":[35],"document":[36],"pairs,":[37],"score":[39],"them":[40],"so":[41],"that":[42],"low-quality":[43],"can":[45],"be":[46],"filtered.":[47],"Our":[48,99],"system,":[49],"Volctrans,":[50],"is":[51],"made":[52],"two":[54],"modules,":[55],"i.e.,":[56],"a":[57,61],"mining":[58,71,77],"module":[59],"scoring":[62,86],"module.":[63],"Based":[64],"word":[67],"model,":[69],"mod-":[72],"ule":[73],"adopts":[74],"an":[75,88],"iterative":[76],"strategy":[78],"extract":[80],"latent":[81],"sentences.":[83],"module,":[87],"XLM-based":[89],"scorer":[90],"provides":[91],"scores,":[92],"followed":[93],"by":[94,104],"reranking":[95],"mechanisms":[96],"ensemble.":[98],"outperform":[101],"baseline":[103],"3.x/2.x":[105],"2.x/2.x":[107],"km-en":[109],"ps-en":[111],"From":[113],"Scratch/Fine-Tune":[114]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2021-01-18T00:00:00"}