{"id":"https://openalex.org/W3183419084","doi":"https://doi.org/10.18653/v1/2021.ecnlp-1.21","title":"Product Review Translation: Parallel Corpus Creation and Robustness towards User-generated Noisy Text","display_name":"Product Review Translation: Parallel Corpus Creation and Robustness towards User-generated Noisy Text","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3183419084","doi":"https://doi.org/10.18653/v1/2021.ecnlp-1.21","mag":"3183419084"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2021.ecnlp-1.21","doi":"https://doi.org/10.18653/v1/2021.ecnlp-1.21","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.ecnlp-1.21","pdf_url":"https://aclanthology.org/2021.ecnlp-1.21.pdf","source":{"id":"https://openalex.org/S7407105602","display_name":"Workshop on e-Commerce and NLP (ECNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 4th Workshop on e-Commerce and NLP","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2021.ecnlp-1.21.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102727211","display_name":"Kamal Kumar Gupta","orcid":"https://orcid.org/0000-0003-0531-2735","observed_orcids":["https://orcid.org/0000-0003-0531-2735"]},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kamal Kumar Gupta","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Patna, Patna, India \u2020 Flipkart, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Patna, Patna, India \u2020 Flipkart, India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059190973","display_name":"Soumya Chennabasavaraj","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Soumya Chennabasavaraj","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Patna, Patna, India \u2020 Flipkart, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Patna, Patna, India \u2020 Flipkart, India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080735926","display_name":"Nikesh Garera","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nikesh Garera","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Patna, Patna, India \u2020 Flipkart, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Patna, Patna, India \u2020 Flipkart, India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085370631","display_name":"Asif Ekbal","orcid":"https://orcid.org/0000-0003-3612-8834","observed_orcids":["https://orcid.org/0000-0003-3612-8834"]},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Asif Ekbal","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Patna, Patna, India \u2020 Flipkart, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Patna, Patna, India \u2020 Flipkart, India","institution_ids":["https://openalex.org/I132153292"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I132153292"],"apc_list":null,"apc_paid":null,"fwci":0.2305,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.43965037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"174","last_page":"183"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9937000274658203,"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":0.9937000274658203,"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":0.0031999999191612005,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0010999999940395355,"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/product-reviews","display_name":"product reviews","score":0.8169999718666077},{"id":"https://openalex.org/keywords/online-consumer-reviews","display_name":"online customer reviews","score":0.6539999842643738},{"id":"https://openalex.org/keywords/multilingual-machine-translation","display_name":"multilingual machine translation","score":0.6679999828338623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8354231119155884},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7978939414024353},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7153973579406738},{"id":"https://openalex.org/C519982507","wikidata":"https://www.wikidata.org/wiki/Q1568","display_name":"Hindi","level":2,"score":0.6759793758392334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6585538983345032},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5051658749580383},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43313878774642944},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.4279754161834717},{"id":"https://openalex.org/C135784402","wikidata":"https://www.wikidata.org/wiki/Q6958279","display_name":"Evaluation of machine translation","level":5,"score":0.4217478632926941},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.2811462879180908},{"id":"https://openalex.org/C148526163","wikidata":"https://www.wikidata.org/wiki/Q6723733","display_name":"Machine translation software usability","level":4,"score":0.2593476176261902},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20649778842926025},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2021.ecnlp-1.21","doi":"https://doi.org/10.18653/v1/2021.ecnlp-1.21","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.ecnlp-1.21","pdf_url":"https://aclanthology.org/2021.ecnlp-1.21.pdf","source":{"id":"https://openalex.org/S7407105602","display_name":"Workshop on e-Commerce and NLP (ECNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 4th Workshop on e-Commerce and NLP","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2021.ecnlp-1.21","doi":"https://doi.org/10.18653/v1/2021.ecnlp-1.21","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.ecnlp-1.21","pdf_url":"https://aclanthology.org/2021.ecnlp-1.21.pdf","source":{"id":"https://openalex.org/S7407105602","display_name":"Workshop on e-Commerce and NLP (ECNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 4th Workshop on e-Commerce and NLP","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3183419084.pdf","grobid_xml":"https://content.openalex.org/works/W3183419084.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W46679369","https://openalex.org/W222053410","https://openalex.org/W2064675550","https://openalex.org/W2626778328","https://openalex.org/W2885950361","https://openalex.org/W2886787567","https://openalex.org/W2889746679","https://openalex.org/W2897105542","https://openalex.org/W2914056350","https://openalex.org/W2916835973","https://openalex.org/W2945808722","https://openalex.org/W2962784628","https://openalex.org/W2963216553","https://openalex.org/W2963661177","https://openalex.org/W2963877297","https://openalex.org/W2964308564","https://openalex.org/W2982616641"],"related_works":["https://openalex.org/W3197322108","https://openalex.org/W4205429521","https://openalex.org/W4385572917","https://openalex.org/W3213848376","https://openalex.org/W2982616641","https://openalex.org/W2970579846","https://openalex.org/W3217292540","https://openalex.org/W4386307686","https://openalex.org/W2250244016","https://openalex.org/W2924093092"],"abstract_inverted_index":{"Reviews":[0],"written":[1,90],"by":[2,80,91,122],"the":[3,16,47,88,92,119,140,148,154,178,182,197,214,225,235],"users":[4,51,93],"for":[5,15,165],"a":[6,60,72,159,186],"particular":[7],"product":[8,141],"or":[9],"service":[10],"play":[11],"an":[12,20,43,81,124,131],"influencing":[13],"role":[14],"customers":[17],"to":[18,62,97,138,169,176,191],"make":[19,63,170],"informative":[21],"decision.Although":[22],"online":[23],"e-commerce":[24,50,145],"portals":[25],"have":[26],"immensely":[27],"impacted":[28],"our":[29,171],"lives,":[30],"available":[31,66,143],"contents":[32],"predominantly":[33],"are":[34,53,224],"in":[35,46,56,67,71,181],"English":[36],"language-often":[37],"limiting":[38],"its":[39],"widespread":[40],"usage.There":[41],"is":[42,59],"exponential":[44],"growth":[45],"number":[48],"of":[49,106,110,161,217,227,238],"who":[52],"not":[54],"proficient":[55],"English.Hence,":[57],"there":[58],"necessity":[61],"these":[64],"services":[65],"non-English":[68],"languages,":[69],"especially":[70],"multilingual":[73],"country":[74],"like":[75],"India.This":[76],"can":[77],"be":[78],"achieved":[79],"in-domain":[82,114],"robust":[83,174],"machine":[84,134],"translation":[85,135],"(MT)":[86],"system.However,":[87],"reviews":[89,142],"pose":[94],"unique":[95],"challenges":[96,121],"MT,":[98],"such":[99,112],"as":[100,113],"misspelled":[101],"words,":[102],"ungrammatical":[103],"constructions,":[104],"presence":[105],"colloquial":[107],"terms,":[108],"lack":[109],"resources":[111],"parallel":[115,128],"corpus":[116],"etc.We":[117],"address":[118],"above":[120],"presenting":[123],"English-Hindi":[125],"review":[126],"domain":[127],"corpus.We":[129],"train":[130],"English-to-Hindi":[132,166],"neural":[133],"(NMT)":[136],"system":[137],"translate":[139],"on":[144,204],"websites.By":[146],"training":[147],"Transformer":[149],"based":[150,188],"NMT":[151,172],"model":[152,173,190],"over":[153,234],"generated":[155],"data,":[156],"we":[157,184],"achieve":[158],"score":[160],"33.26":[162],"BLEU":[163],"points":[164],"translation.In":[167],"order":[168],"enough":[175],"handle":[177],"noisy":[179,198],"tokens":[180,199],"reviews,":[183],"integrate":[185],"character":[187],"language":[189,206],"generate":[192],"word":[193],"vectors":[194],"and":[195,211,221,231],"map":[196],"with":[200],"their":[201],"correct":[202],"forms.Experiments":[203],"four":[205],"pairs,":[207],"viz.English-Hindi,":[208],"English-German,":[209],"English-French,":[210],"English-Czech":[212],"show":[213],"BLUE":[215],"scores":[216],"35.09,":[218],"28.91,":[219],"34.68":[220],"14.52":[222],"which":[223],"improvements":[226],"1.61,":[228],"1.05,":[229],"1.63":[230],"1.94,":[232],"respectively,":[233],"baseline.":[236],"Type":[237],"noise":[239],"Example":[240]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2021-08-02T00:00:00"}