{"id":"https://openalex.org/W2905134510","doi":"https://doi.org/10.1145/3265751","title":"Pause-Based Phrase Extraction and Effective OOV Handling for Low-Resource Machine Translation Systems","display_name":"Pause-Based Phrase Extraction and Effective OOV Handling for Low-Resource Machine Translation Systems","publication_year":2018,"publication_date":"2018-12-14","ids":{"openalex":"https://openalex.org/W2905134510","doi":"https://doi.org/10.1145/3265751","mag":"2905134510"},"language":"en","primary_location":{"id":"doi:10.1145/3265751","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3265751","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111148465","display_name":"K. Mrinalini","orcid":null},"institutions":[{"id":"https://openalex.org/I916357946","display_name":"Sri Sivasubramaniya Nadar College of Engineering","ror":"https://ror.org/054psm803","country_code":"IN","type":"education","lineage":["https://openalex.org/I916357946"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"K. Mrinalini","raw_affiliation_strings":["SSN College of Engineering, India"],"raw_orcid":"https://orcid.org/0000-0003-4632-2518","affiliations":[{"raw_affiliation_string":"SSN College of Engineering, India","institution_ids":["https://openalex.org/I916357946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080103016","display_name":"T. Nagarajan","orcid":null},"institutions":[{"id":"https://openalex.org/I916357946","display_name":"Sri Sivasubramaniya Nadar College of Engineering","ror":"https://ror.org/054psm803","country_code":"IN","type":"education","lineage":["https://openalex.org/I916357946"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"T. Nagarajan","raw_affiliation_strings":["SSN College of Engineering, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SSN College of Engineering, India","institution_ids":["https://openalex.org/I916357946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035034970","display_name":"P. Vijayalakshmi","orcid":"https://orcid.org/0000-0003-3171-0219"},"institutions":[{"id":"https://openalex.org/I916357946","display_name":"Sri Sivasubramaniya Nadar College of Engineering","ror":"https://ror.org/054psm803","country_code":"IN","type":"education","lineage":["https://openalex.org/I916357946"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"P. Vijayalakshmi","raw_affiliation_strings":["SSN College of Engineering, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SSN College of Engineering, India","institution_ids":["https://openalex.org/I916357946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I916357946"],"apc_list":null,"apc_paid":null,"fwci":0.5599,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.77572592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"18","issue":"2","first_page":"1","last_page":"22"},"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":0.9994000196456909,"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/T13629","display_name":"Text Readability and Simplification","score":0.9854999780654907,"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":0.8567043542861938},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7474442720413208},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7449039220809937},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7348389029502869},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6897755861282349},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.5216662883758545},{"id":"https://openalex.org/keywords/machine-translation-software-usability","display_name":"Machine translation software usability","score":0.5052030682563782},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4823310077190399},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.4730742871761322},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4597731828689575},{"id":"https://openalex.org/keywords/transliteration","display_name":"Transliteration","score":0.44724714756011963},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44096267223358154},{"id":"https://openalex.org/keywords/synchronous-context-free-grammar","display_name":"Synchronous context-free grammar","score":0.4195188283920288},{"id":"https://openalex.org/keywords/computer-assisted-translation","display_name":"Computer-assisted translation","score":0.4118348956108093},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39938217401504517},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07879427075386047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8567043542861938},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7474442720413208},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7449039220809937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7348389029502869},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6897755861282349},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.5216662883758545},{"id":"https://openalex.org/C148526163","wikidata":"https://www.wikidata.org/wiki/Q6723733","display_name":"Machine translation software usability","level":4,"score":0.5052030682563782},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4823310077190399},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.4730742871761322},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4597731828689575},{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.44724714756011963},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44096267223358154},{"id":"https://openalex.org/C51802942","wikidata":"https://www.wikidata.org/wiki/Q7662211","display_name":"Synchronous context-free grammar","level":4,"score":0.4195188283920288},{"id":"https://openalex.org/C110046852","wikidata":"https://www.wikidata.org/wiki/Q468495","display_name":"Computer-assisted translation","level":3,"score":0.4118348956108093},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39938217401504517},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07879427075386047},{"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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:10.1145/3265751","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3265751","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W629724564","https://openalex.org/W1489501102","https://openalex.org/W1508577659","https://openalex.org/W1599204704","https://openalex.org/W1767788615","https://openalex.org/W1994581546","https://openalex.org/W2018869373","https://openalex.org/W2031807157","https://openalex.org/W2054549124","https://openalex.org/W2093790824","https://openalex.org/W2101105183","https://openalex.org/W2108460050","https://openalex.org/W2124807415","https://openalex.org/W2130942839","https://openalex.org/W2149327368","https://openalex.org/W2153653739","https://openalex.org/W2153903004","https://openalex.org/W2156984567","https://openalex.org/W2166776180","https://openalex.org/W2218202018","https://openalex.org/W2340598284","https://openalex.org/W2404928265","https://openalex.org/W2510502404","https://openalex.org/W2566490639","https://openalex.org/W2575483272","https://openalex.org/W2587014613","https://openalex.org/W2797799654","https://openalex.org/W6703786030"],"related_works":["https://openalex.org/W3036784334","https://openalex.org/W3204448004","https://openalex.org/W2566847733","https://openalex.org/W2010336863","https://openalex.org/W2122287718","https://openalex.org/W2740094425","https://openalex.org/W2184842915","https://openalex.org/W2383963481","https://openalex.org/W2407077619","https://openalex.org/W4321010057"],"abstract_inverted_index":{"Machine":[0],"translation":[1,18,31,45,48,160,169,181,200,220],"is":[2,71,109,112,171,210,229],"the":[3,13,38,62,67,83,89,92,116,121,141,145,151,162,175,208,232],"core":[4],"problem":[5],"for":[6,47,87,119,222],"several":[7],"natural":[8],"language":[9,69,78,225],"processing":[10],"research":[11],"across":[12],"globe.":[14],"However,":[15],"building":[16],"a":[17,24,41,54,75,95,165,191,199],"system":[19,46,188,209,234],"involving":[20],"low-resource":[21,55],"languages":[22,108],"remains":[23],"challenge":[25],"with":[26,153,218],"respect":[27],"to":[28,51,73,81,114,173],"statistical":[29],"machine":[30,44,168],"(SMT).":[32],"This":[33],"work":[34],"proposes":[35],"and":[36,80,104,134,179,198,216,227],"studies":[37],"effect":[39],"of":[40,66,144,196,203,207,214],"phrase-induced":[42,123],"hybrid":[43,59],"from":[49],"English":[50],"Tamil,":[52],"under":[53],"setting.":[56],"Unlike":[57],"conventional":[58],"MT":[60],"systems,":[61],"free-word":[63],"ordering":[64],"feature":[65],"target":[68,77],"Tamil":[70],"exploited":[72],"form":[74],"re-ordered":[76],"model":[79],"extend":[82],"parallel":[84],"text":[85],"corpus":[86,118],"training":[88,117],"SMT.":[90,124],"In":[91],"current":[93],"work,":[94],"novel":[96],"rule-based":[97],"phrase-extraction":[98],"method,":[99],"implemented":[100],"using":[101,131],"parts-of-speech":[102],"(POS)":[103],"place-of-pause":[105],"in":[106,161,190,212],"both":[107],"proposed,":[110],"which":[111],"used":[113],"pre-process":[115],"developing":[120],"back-off":[122],"Further,":[125],"out-of-vocabulary":[126],"(OOV)":[127],"words":[128,155],"are":[129],"handled":[130],"speech-based":[132],"transliteration":[133],"two-level":[135],"thesaurus":[136],"intersection":[137],"techniques":[138],"based":[139],"on":[140],"POS":[142],"tag":[143],"OOV":[146,154,184],"word.":[147],"To":[148],"ensure":[149],"that":[150,231],"input":[152],"does":[156],"not":[157],"skip":[158],"phrase-level":[159,166],"hierarchical":[163],"model,":[164],"example-based":[167],"approach":[170],"adopted":[172],"find":[174],"closest":[176],"matching":[177],"phrase":[178],"perform":[180],"followed":[182],"by":[183],"replacement.":[185],"The":[186,205],"proposed":[187,233],"results":[189],"bilingual":[192],"evaluation":[193],"understudy":[194],"score":[195],"84.78":[197],"edit":[201],"rate":[202],"19.12.":[204],"performance":[206],"compared":[211],"terms":[213],"adequacy":[215],"fluency,":[217],"existing":[219],"systems":[221],"this":[223],"specific":[224],"pair,":[226],"it":[228],"observed":[230],"outperforms":[235],"its":[236],"counterparts.":[237]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
