{"id":"https://openalex.org/W3048539749","doi":"https://doi.org/10.1145/3430984.3431026","title":"Revisiting Low Resource Status of Indian Languages in Machine Translation","display_name":"Revisiting Low Resource Status of Indian Languages in Machine Translation","publication_year":2020,"publication_date":"2020-12-28","ids":{"openalex":"https://openalex.org/W3048539749","doi":"https://doi.org/10.1145/3430984.3431026","mag":"3048539749"},"language":"en","primary_location":{"id":"doi:10.1145/3430984.3431026","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3430984.3431026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM India Joint International Conference on Data Science & Management of Data (8th ACM IKDD CODS & 26th COMAD)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.04860","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jerin Philip","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Jerin Philip","raw_affiliation_strings":["IIIT Hyderabad"],"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shashank Siripragada","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shashank Siripragada","raw_affiliation_strings":["IIIT Hyderabad"],"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Vinay P. Namboodiri","orcid":null},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vinay P. Namboodiri","raw_affiliation_strings":["IIT Kanpur"],"affiliations":[{"raw_affiliation_string":"IIT Kanpur","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"last","author":{"id":null,"display_name":"C. V. Jawahar","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"C. V. Jawahar","raw_affiliation_strings":["IIIT Hyderabad"],"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I65181880"],"apc_list":null,"apc_paid":null,"fwci":1.6458,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.87339664,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"178","last_page":"187"},"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":0.9990000128746033,"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":0.9843000173568726,"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/machine-translation","display_name":"Machine translation","score":0.8310999870300293},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7731000185012817},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.567799985408783},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5529000163078308},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4894999861717224},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.47920000553131104},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4120999872684479},{"id":"https://openalex.org/keywords/machine-translation-software-usability","display_name":"Machine translation software usability","score":0.40290001034736633}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8310999870300293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8203999996185303},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7731000185012817},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6541000008583069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6126999855041504},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.567799985408783},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5529000163078308},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4894999861717224},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.47920000553131104},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4120999872684479},{"id":"https://openalex.org/C148526163","wikidata":"https://www.wikidata.org/wiki/Q6723733","display_name":"Machine translation software usability","level":4,"score":0.40290001034736633},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.38960000872612},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.37950000166893005},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C135784402","wikidata":"https://www.wikidata.org/wiki/Q6958279","display_name":"Evaluation of machine translation","level":5,"score":0.36149999499320984},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.3370000123977661},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3357999920845032},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.2583000063896179}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3430984.3431026","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3430984.3431026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM India Joint International Conference on Data Science & Management of Data (8th ACM IKDD CODS & 26th COMAD)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.04860","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.04860","pdf_url":"https://arxiv.org/pdf/2008.04860","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.04860","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.04860","pdf_url":"https://arxiv.org/pdf/2008.04860","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1489181569","https://openalex.org/W2080179390","https://openalex.org/W2465297109","https://openalex.org/W2511852057","https://openalex.org/W2889326796","https://openalex.org/W2892009878","https://openalex.org/W2919290281","https://openalex.org/W2933138175","https://openalex.org/W2949973181","https://openalex.org/W2963216553","https://openalex.org/W2963347649","https://openalex.org/W2963402313","https://openalex.org/W2963506925","https://openalex.org/W2963532001","https://openalex.org/W2963729818","https://openalex.org/W2963807318","https://openalex.org/W2964091381","https://openalex.org/W2970295111","https://openalex.org/W2970731908","https://openalex.org/W2970925270","https://openalex.org/W2983183316","https://openalex.org/W3035032094","https://openalex.org/W3099919888","https://openalex.org/W3113698880","https://openalex.org/W6744973198","https://openalex.org/W6767250937"],"related_works":[],"abstract_inverted_index":{"Indian":[0,37,163],"language":[1,38,126],"machine":[2,40],"translation":[3,41],"performance":[4],"is":[5,60,81],"hampered":[6],"due":[7],"to":[8,31,62,82,92,141,156],"the":[9,73,89,95,98,106,117,122,128,174],"lack":[10],"of":[11,47,97,105,108,124,130],"large":[12],"scale":[13],"multi-lingual":[14],"sentence":[15],"aligned":[16],"corpora":[17,158],"and":[18,26,55,127,180],"robust":[19],"benchmarks.":[20,184],"Through":[21,111],"this":[22,79],"paper,":[23],"we":[24,114],"provide":[25],"analyse":[27],"an":[28,56,84,143],"automated":[29,144],"framework":[30,145],"obtain":[32,83,169],"such":[33,68,120],"a":[34,48,52,150],"corpus":[35,99,135,153,166],"for":[36,162],"neural":[39],"(NMT)":[42],"systems.":[43],"Our":[44,137],"pipeline":[45,91],"consists":[46],"baseline":[49],"NMT":[50],"system,":[51],"retrieval":[53],"module,":[54],"alignment":[57],"module":[58],"that":[59,87,159],"used":[61],"work":[63,138],"with":[64],"publicly":[65,175],"available":[66,161,176],"websites":[67],"as":[69,100,102,121,154],"press":[70],"releases":[71],"by":[72],"government.":[74],"The":[75],"main":[76],"contribution":[77],"towards":[78],"effort":[80],"incremental":[85,132],"method":[86],"uses":[88],"above":[90],"iteratively":[93],"improve":[94,103],"size":[96],"well":[101],"each":[104],"components":[107],"our":[109,112],"system.":[110],"work,":[113],"also":[115,146],"evaluate":[116],"design":[118],"choices":[119],"choice":[123],"pivoting":[125],"effect":[129],"iterative":[131],"increase":[133],"in":[134,139,148],"size.":[136],"addition":[140],"providing":[142],"results":[147,172],"generating":[149],"relatively":[151],"larger":[152],"compared":[155],"existing":[157],"are":[160],"languages.":[164],"This":[165],"helps":[167],"us":[168],"substantially":[170],"improved":[171],"on":[173],"WAT":[177],"evaluation":[178,183],"benchmark":[179],"other":[181],"standard":[182]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2020-08-18T00:00:00"}