{"id":"https://openalex.org/W4411638727","doi":"https://doi.org/10.18653/v1/2024.eacl-short.27","title":"Robust Neural Machine Translation for Abugidas by Glyph Perturbation","display_name":"Robust Neural Machine Translation for Abugidas by Glyph Perturbation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4411638727","doi":"https://doi.org/10.18653/v1/2024.eacl-short.27"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.eacl-short.27","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-short.27","pdf_url":"https://aclanthology.org/2024.eacl-short.27.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 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.eacl-short.27.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083898578","display_name":"Hour Kaing","orcid":"https://orcid.org/0000-0003-4389-2144"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hour Kaing","raw_affiliation_strings":["Advanced Translation Technology Laboratory , Advanced Speech Translation Research and Development Promotion Center , National Institute of Information and Communications Technology , 3-5 Hikaridai , Seika-cho , Soraku-gun , Kyoto , 619-0289 , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Translation Technology Laboratory , Advanced Speech Translation Research and Development Promotion Center , National Institute of Information and Communications Technology , 3-5 Hikaridai , Seika-cho , Soraku-gun , Kyoto , 619-0289 , Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001889488","display_name":"Chenchen Ding","orcid":"https://orcid.org/0000-0002-7523-208X"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chenchen Ding","raw_affiliation_strings":["Advanced Translation Technology Laboratory , Advanced Speech Translation Research and Development Promotion Center , National Institute of Information and Communications Technology , 3-5 Hikaridai , Seika-cho , Soraku-gun , Kyoto , 619-0289 , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Translation Technology Laboratory , Advanced Speech Translation Research and Development Promotion Center , National Institute of Information and Communications Technology , 3-5 Hikaridai , Seika-cho , Soraku-gun , Kyoto , 619-0289 , Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031493092","display_name":"Hideki Tanaka","orcid":"https://orcid.org/0000-0003-2099-8990"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideki Tanaka","raw_affiliation_strings":["Advanced Translation Technology Laboratory , Advanced Speech Translation Research and Development Promotion Center , National Institute of Information and Communications Technology , 3-5 Hikaridai , Seika-cho , Soraku-gun , Kyoto , 619-0289 , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Translation Technology Laboratory , Advanced Speech Translation Research and Development Promotion Center , National Institute of Information and Communications Technology , 3-5 Hikaridai , Seika-cho , Soraku-gun , Kyoto , 619-0289 , Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021667085","display_name":"Masao Utiyama","orcid":"https://orcid.org/0000-0003-1111-9245"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masao Utiyama","raw_affiliation_strings":["Advanced Translation Technology Laboratory , Advanced Speech Translation Research and Development Promotion Center , National Institute of Information and Communications Technology , 3-5 Hikaridai , Seika-cho , Soraku-gun , Kyoto , 619-0289 , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Translation Technology Laboratory , Advanced Speech Translation Research and Development Promotion Center , National Institute of Information and Communications Technology , 3-5 Hikaridai , Seika-cho , Soraku-gun , Kyoto , 619-0289 , Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26060106,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"311","last_page":"318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9763000011444092,"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":0.9763000011444092,"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/computer-science","display_name":"Computer science","score":0.7163269519805908},{"id":"https://openalex.org/keywords/glyph","display_name":"Glyph (data visualization)","score":0.6799449920654297},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6674536466598511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4745905101299286},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41663044691085815},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.1846875250339508}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7163269519805908},{"id":"https://openalex.org/C142816647","wikidata":"https://www.wikidata.org/wiki/Q5573018","display_name":"Glyph (data visualization)","level":3,"score":0.6799449920654297},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6674536466598511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4745905101299286},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41663044691085815},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.1846875250339508}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.eacl-short.27","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-short.27","pdf_url":"https://aclanthology.org/2024.eacl-short.27.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 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.eacl-short.27","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-short.27","pdf_url":"https://aclanthology.org/2024.eacl-short.27.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 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411638727.pdf","grobid_xml":"https://content.openalex.org/works/W4411638727.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W2933138175"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2971077392","https://openalex.org/W2350760135","https://openalex.org/W2090371563","https://openalex.org/W1972316918","https://openalex.org/W4312601913","https://openalex.org/W4212776738","https://openalex.org/W2786162233"],"abstract_inverted_index":{"Neural":[0],"machine":[1],"translation":[2],"(NMT)":[3],"systems":[4,49,117],"are":[5],"vulnerable":[6],"when":[7],"trained":[8],"on":[9,61,99],"limited":[10],"data.This":[11],"is":[12,27,75],"a":[13,25,91],"common":[14],"scenario":[15],"in":[16,19,33,47],"low-resource":[17,122],"tasks":[18,123],"the":[20,34,69,79,86,110],"real":[21],"world.To":[22],"increase":[23],"robustness,":[24],"solution":[26],"to":[28,44,77,94],"intently":[29],"add":[30],"realistic":[31],"noise":[32],"training":[35,92],"phase.Noise":[36],"simulation":[37],"using":[38],"text":[39],"perturbation":[40,59],"has":[41],"been":[42],"proven":[43],"be":[45],"efficient":[46],"writing":[48,65,84],"that":[50],"use":[51],"Latin":[52],"letters.In":[53],"this":[54],"study,":[55],"we":[56,89,113],"further":[57],"explore":[58],"techniques":[60],"more":[62],"complex":[63,73],"abugida":[64,125],"systems,":[66],"for":[67,121,124],"which":[68],"visual":[70],"similarity":[71],"of":[72,82],"glyphs":[74],"considered":[76],"capture":[78],"essential":[80],"nature":[81],"these":[83],"systems.Besides":[85],"generated":[87],"noise,":[88,112],"propose":[90],"strategy":[93],"improve":[95],"robustness.We":[96],"conducted":[97],"experiments":[98],"six":[100],"languages:":[101],"Bengali,":[102],"Hindi,":[103],"Myanmar,":[104],"Khmer,":[105],"Lao,":[106],"and":[107],"Thai.By":[108],"overcoming":[109],"introduced":[111],"obtained":[114],"non-degenerate":[115],"NMT":[116],"with":[118],"improved":[119],"robustness":[120],"glyphs.":[126]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
