{"id":"https://openalex.org/W3208306779","doi":"https://doi.org/10.48550/arxiv.2111.00191","title":"How should human translation coexist with NMT? Efficient tool for building high quality parallel corpus","display_name":"How should human translation coexist with NMT? Efficient tool for building high quality parallel corpus","publication_year":2021,"publication_date":"2021-10-30","ids":{"openalex":"https://openalex.org/W3208306779","doi":"https://doi.org/10.48550/arxiv.2111.00191","mag":"3208306779"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2111.00191","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.00191","pdf_url":"https://arxiv.org/pdf/2111.00191","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2111.00191","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003145618","display_name":"Chanjun Park","orcid":"https://orcid.org/0000-0002-7200-9632","observed_orcids":["https://orcid.org/0000-0002-7200-9632"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Park, Chanjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068060125","display_name":"Seolhwa Lee","orcid":"https://orcid.org/0000-0002-8109-8497","observed_orcids":["https://orcid.org/0000-0002-8109-8497"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Seolhwa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048597650","display_name":"Hyeonseok Moon","orcid":"https://orcid.org/0000-0002-0841-4262","observed_orcids":["https://orcid.org/0000-0002-0841-4262"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moon, Hyeonseok","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080903430","display_name":"Sugyeong Eo","orcid":"https://orcid.org/0000-0002-8008-6160","observed_orcids":["https://orcid.org/0000-0002-8008-6160"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eo, Sugyeong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014883878","display_name":"Jaehyung Seo","orcid":"https://orcid.org/0000-0002-4761-9818","observed_orcids":["https://orcid.org/0000-0002-4761-9818"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seo, Jaehyung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5033580486","display_name":"Heuiseok Lim","orcid":"https://orcid.org/0000-0002-9269-1157","observed_orcids":["https://orcid.org/0000-0002-9269-1157"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lim, Heuiseok","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"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":0.9980000257492065,"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/T10759","display_name":"Translation Studies and Practices","score":0.0013000000035390258,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.00019999999494757503,"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/parallel-corpus-construction","display_name":"parallel corpus construction","score":0.9710000157356262},{"id":"https://openalex.org/keywords/neural-machine-translation","display_name":"neural machine translation","score":0.9660000205039978},{"id":"https://openalex.org/keywords/human-translation","display_name":"human translation","score":0.8830000162124634},{"id":"https://openalex.org/keywords/data-quality-control","display_name":"data quality control","score":0.9459999799728394},{"id":"https://openalex.org/keywords/low-resource-language-translation","display_name":"low-resource translation","score":0.41200000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7858555316925049},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.7570356130599976},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6877557635307312},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6398466229438782},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5597067475318909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5380653142929077},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4786830544471741},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.46723777055740356},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35913538932800293},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10082748532295227},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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":3,"locations":[{"id":"pmh:oai:arXiv.org:2111.00191","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.00191","pdf_url":"https://arxiv.org/pdf/2111.00191","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3208306779","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2111.00191","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2111.00191","doi":"https://doi.org/10.48550/arxiv.2111.00191","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2111.00191","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2111.00191","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.00191","pdf_url":"https://arxiv.org/pdf/2111.00191","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2168305914","https://openalex.org/W2904817079","https://openalex.org/W2970871182","https://openalex.org/W2971120958","https://openalex.org/W3024508854","https://openalex.org/W3028827502","https://openalex.org/W3113819942","https://openalex.org/W3116506157","https://openalex.org/W3119872155","https://openalex.org/W3120896619","https://openalex.org/W3120955312","https://openalex.org/W3171405214","https://openalex.org/W3187058997"],"related_works":["https://openalex.org/W3027029340","https://openalex.org/W4386093753","https://openalex.org/W4412944227","https://openalex.org/W7005470792","https://openalex.org/W4366308792","https://openalex.org/W2107695330","https://openalex.org/W4406827094","https://openalex.org/W2104907655","https://openalex.org/W4404781966","https://openalex.org/W3212231182"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,57],"tool":[4,18],"for":[5,34],"efficiently":[6],"constructing":[7],"high-quality":[8],"parallel":[9],"corpora":[10],"with":[11,40,53],"minimizing":[12],"human":[13,41,54],"labor":[14],"and":[15],"making":[16],"this":[17],"publicly":[19],"available.":[20],"Our":[21],"proposed":[22],"construction":[23],"process":[24],"is":[25],"based":[26],"on":[27],"neural":[28],"machine":[29],"translation":[30,55],"(NMT)":[31],"to":[32,36],"allow":[33],"it":[35],"not":[37],"only":[38],"coexist":[39],"translation,":[42],"but":[43],"also":[44],"improve":[45],"its":[46],"efficiency":[47],"by":[48],"combining":[49],"data":[50],"quality":[51],"control":[52],"in":[56],"data-centric":[58],"approach.":[59]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-11-08T00:00:00"}