{"id":"https://openalex.org/W2962733029","doi":"https://doi.org/10.18653/v1/w18-6107","title":"Normalization of Transliterated Words in Code-Mixed Data Using Seq2Seq Model & Levenshtein Distance","display_name":"Normalization of Transliterated Words in Code-Mixed Data Using Seq2Seq Model & Levenshtein Distance","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2962733029","doi":"https://doi.org/10.18653/v1/w18-6107","mag":"2962733029"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-6107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6107","pdf_url":"https://www.aclweb.org/anthology/W18-6107.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 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-6107.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029697503","display_name":"Soumil Mandal","orcid":null},"institutions":[{"id":"https://openalex.org/I145286018","display_name":"SRM Institute of Science and Technology","ror":"https://ror.org/050113w36","country_code":"IN","type":"education","lineage":["https://openalex.org/I145286018"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Soumil Mandal","raw_affiliation_strings":["Department of Computer Science & Engineering SRM Institute of Science & Technology, Chennai, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering SRM Institute of Science & Technology, Chennai, India","institution_ids":["https://openalex.org/I145286018"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006291239","display_name":"Karthick Nanmaran","orcid":null},"institutions":[{"id":"https://openalex.org/I145286018","display_name":"SRM Institute of Science and Technology","ror":"https://ror.org/050113w36","country_code":"IN","type":"education","lineage":["https://openalex.org/I145286018"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Karthick Nanmaran","raw_affiliation_strings":["Department of Computer Science & Engineering SRM Institute of Science & Technology, Chennai, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering SRM Institute of Science & Technology, Chennai, India","institution_ids":["https://openalex.org/I145286018"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029697503"],"corresponding_institution_ids":["https://openalex.org/I145286018"],"apc_list":null,"apc_paid":null,"fwci":0.9773,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.8279914,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"49","last_page":"53"},"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":0.9988999962806702,"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":0.9975000023841858,"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/levenshtein-distance","display_name":"Levenshtein distance","score":0.8356740474700928},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8028253316879272},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6500627398490906},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.6250338554382324},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6158953905105591},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5512630343437195},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.5332987308502197},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5157352089881897},{"id":"https://openalex.org/keywords/transliteration","display_name":"Transliteration","score":0.5079699158668518},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4838051199913025},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.44455888867378235},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.4431181848049164},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4136108458042145},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3849225640296936},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.20806291699409485},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14736050367355347},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09635990858078003}],"concepts":[{"id":"https://openalex.org/C2777515626","wikidata":"https://www.wikidata.org/wiki/Q496939","display_name":"Levenshtein distance","level":2,"score":0.8356740474700928},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8028253316879272},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6500627398490906},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.6250338554382324},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6158953905105591},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5512630343437195},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5332987308502197},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5157352089881897},{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.5079699158668518},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4838051199913025},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.44455888867378235},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.4431181848049164},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4136108458042145},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3849225640296936},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20806291699409485},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14736050367355347},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09635990858078003},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w18-6107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6107","pdf_url":"https://www.aclweb.org/anthology/W18-6107.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 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-6107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6107","pdf_url":"https://www.aclweb.org/anthology/W18-6107.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 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2962733029.pdf","grobid_xml":"https://content.openalex.org/works/W2962733029.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1552936656","https://openalex.org/W1647671624","https://openalex.org/W2097478551","https://openalex.org/W2130942839","https://openalex.org/W2164107060","https://openalex.org/W2251237590","https://openalex.org/W2338893019","https://openalex.org/W2525997790","https://openalex.org/W2531207078","https://openalex.org/W2546744831","https://openalex.org/W2554000662","https://openalex.org/W2747175885","https://openalex.org/W2776429271","https://openalex.org/W2783228166","https://openalex.org/W2791704856","https://openalex.org/W2793276877","https://openalex.org/W2795670164","https://openalex.org/W2963293280","https://openalex.org/W2963403868","https://openalex.org/W4295276571","https://openalex.org/W4322019472","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2461708070","https://openalex.org/W2003932770","https://openalex.org/W4362583275","https://openalex.org/W2575897682","https://openalex.org/W2844405045","https://openalex.org/W4285090010","https://openalex.org/W4280559639","https://openalex.org/W4321609555","https://openalex.org/W1531307672","https://openalex.org/W2788104449"],"abstract_inverted_index":{"Building":[0],"tools":[1],"for":[2,46,90],"code-mixed":[3,25,69],"data":[4,16,26],"is":[5,17,65,79],"rapidly":[6],"gaining":[7],"popularity":[8],"in":[9,38,68,81,95],"the":[10,42,73,106],"NLP":[11],"research":[12],"community":[13],"as":[14],"such":[15],"exponentially":[18],"rising":[19],"on":[20,59,105],"social":[21,47],"media.":[22],"Working":[23],"with":[24],"contains":[27],"several":[28],"challenges,":[29],"especially":[30],"due":[31],"to":[32,40,83],"grammatical":[33],"inconsistencies":[34],"and":[35,92],"spelling":[36],"variations":[37],"addition":[39,82],"all":[41],"previous":[43],"known":[44],"challenges":[45],"media":[48],"scenarios.":[49],"In":[50],"this":[51],"article,":[52],"we":[53],"present":[54],"a":[55],"novel":[56],"architecture":[57,78],"focusing":[58],"normalizing":[60],"phonetic":[61],"typing":[62],"variations,":[63],"which":[64],"commonly":[66],"seen":[67],"data.":[70,108],"One":[71],"of":[72,76,103],"main":[74],"features":[75],"our":[77],"that":[80],"normalizing,":[84],"it":[85],"can":[86],"also":[87],"be":[88],"utilized":[89],"back-transliteration":[91],"word":[93],"identification":[94],"some":[96],"cases.":[97],"Our":[98],"model":[99],"achieved":[100],"an":[101],"accuracy":[102],"90.27%":[104],"test":[107]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}