{"id":"https://openalex.org/W3119629808","doi":"https://doi.org/10.18653/v1/2020.wmt-1.9","title":"Linguistically Motivated Subwords for English-Tamil Translation: University of Groningen\u2019s Submission to WMT-2020","display_name":"Linguistically Motivated Subwords for English-Tamil Translation: University of Groningen\u2019s Submission to WMT-2020","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3119629808","doi":"https://doi.org/10.18653/v1/2020.wmt-1.9","mag":"3119629808"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.wmt-1.9","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.9","pdf_url":"https://aclanthology.org/2020.wmt-1.9.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-1.9.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085961012","display_name":"Prajit Dhar","orcid":"https://orcid.org/0000-0002-2809-2192"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Prajit Dhar","raw_affiliation_strings":["Leiden University, Leiden, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leiden University, Leiden, Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019968969","display_name":"Arianna Bisazza","orcid":"https://orcid.org/0000-0003-1270-3048"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Arianna Bisazza","raw_affiliation_strings":["University of Groningen, Groningen, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Groningen, Groningen, Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047337772","display_name":"Gertjan van Noord","orcid":"https://orcid.org/0000-0001-5564-6341"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Gertjan van Noord","raw_affiliation_strings":["University of Groningen, Groningen, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Groningen, Groningen, Netherlands","institution_ids":["https://openalex.org/I169381384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"126","last_page":"133"},"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":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/tamil","display_name":"Tamil","score":0.9020015597343445},{"id":"https://openalex.org/keywords/agglutinative-language","display_name":"Agglutinative language","score":0.7553764581680298},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7333583831787109},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7234768271446228},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6798561215400696},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6259236335754395},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5385504961013794},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.48414474725723267},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44370681047439575},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4429889917373657},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4026845693588257},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2796427011489868},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2453780472278595}],"concepts":[{"id":"https://openalex.org/C140688305","wikidata":"https://www.wikidata.org/wiki/Q5885","display_name":"Tamil","level":2,"score":0.9020015597343445},{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.7553764581680298},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7333583831787109},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7234768271446228},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6798561215400696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6259236335754395},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5385504961013794},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.48414474725723267},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44370681047439575},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4429889917373657},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4026845693588257},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2796427011489868},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2453780472278595},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2020.wmt-1.9","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.9","pdf_url":"https://aclanthology.org/2020.wmt-1.9.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":"pmh:oai:pure.rug.nl:openaire/4a8393cd-5bb6-4afd-82b0-2f2ff6eea47d","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/4a8393cd-5bb6-4afd-82b0-2f2ff6eea47d","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"mag:3119629808","is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/2020.wmt-1.9.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-1.9","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.9","pdf_url":"https://aclanthology.org/2020.wmt-1.9.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/4","score":0.8199999928474426,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2354335809","display_name":"Connecting the Dots: Minimal Structure Modeling for Machine Translation","funder_award_id":"639.021.646","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320320933","display_name":"Rijksuniversiteit Groningen","ror":"https://ror.org/012p63287"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3119629808.pdf"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1905100302","https://openalex.org/W2156984567","https://openalex.org/W2165698076","https://openalex.org/W2250342921","https://openalex.org/W2902614977","https://openalex.org/W2933138175","https://openalex.org/W2962784628","https://openalex.org/W2962801832","https://openalex.org/W2963216553","https://openalex.org/W2963250244","https://openalex.org/W2963266340","https://openalex.org/W2964053711","https://openalex.org/W2970015022","https://openalex.org/W2977259764","https://openalex.org/W2978647884","https://openalex.org/W2978922291","https://openalex.org/W2982685391","https://openalex.org/W2987149083"],"related_works":["https://openalex.org/W2971073020","https://openalex.org/W2971345087","https://openalex.org/W2963329925","https://openalex.org/W2902798232","https://openalex.org/W2735139879","https://openalex.org/W2316776689","https://openalex.org/W2116029204","https://openalex.org/W2970152385","https://openalex.org/W2971031401","https://openalex.org/W2970410759","https://openalex.org/W2160922317","https://openalex.org/W3119625789","https://openalex.org/W2034848062","https://openalex.org/W2790725938","https://openalex.org/W2915824390","https://openalex.org/W2251507105","https://openalex.org/W2511117522","https://openalex.org/W2137148130","https://openalex.org/W2140826881","https://openalex.org/W2970852256"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"our":[3,24,37],"submission":[4],"for":[5],"the":[6,56,69],"English-Tamil":[7],"news":[8],"translation":[9],"task":[10],"of":[11,72],"WMT-2020.":[12],"The":[13],"various":[14],"techniques":[15],"and":[16,28,33,65],"Neural":[17],"Machine":[18],"Translation":[19],"(NMT)":[20],"models":[21],"used":[22],"by":[23],"team":[25],"are":[26],"presented":[27],"discussed,":[29],"including":[30],"back-translation,":[31],"fine-tuning":[32],"word":[34],"dropout.":[35],"Additionally,":[36],"experiments":[38],"show":[39],"that":[40],"using":[41],"a":[42],"linguistically":[43],"motivated":[44,61],"subword":[45],"segmentation":[46],"technique":[47],"(Ataman":[48],"et":[49],"al.,":[50],"2017)":[51],"does":[52],"not":[53],"consistently":[54],"outperform":[55],"more":[57],"widely":[58],"used,":[59],"non-linguistically":[60],"SentencePiece":[62],"algorithm":[63],"(Kudo":[64],"Richardson,":[66],"2018),":[67],"despite":[68],"agglutinative":[70],"nature":[71],"Tamil":[73],"morphology.":[74]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2021-01-18T00:00:00"}
