{"id":"https://openalex.org/W2172268343","doi":null,"title":"Domain Adaptation for Machine Translation by Mining Unseen Words","display_name":"Domain Adaptation for Machine Translation by Mining Unseen Words","publication_year":2011,"publication_date":"2011-06-19","ids":{"openalex":"https://openalex.org/W2172268343","mag":"2172268343"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.207.6219","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.207.6219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology-new/P/P11/P11-2071.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5019928111","display_name":"Hal Daum\u00e9","orcid":"https://orcid.org/0000-0002-3760-345X","observed_orcids":["https://orcid.org/0000-0002-3760-345X"]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hal Daum\u00e9","raw_affiliation_strings":["University of Maryland, Collge Park#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, Collge Park#TAB#","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079876535","display_name":"Jagadeesh Jagarlamudi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jagadeesh Jagarlamudi","raw_affiliation_strings":["University of Maryland - College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland - College Park","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":16.0195,"has_fulltext":false,"cited_by_count":133,"citation_normalized_percentile":{"value":0.99416657,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"407","last_page":"412"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"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":0.9980000257492065,"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/T10759","display_name":"Translation Studies and Practices","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.00039999998989515007,"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/domain-adaptation","display_name":"domain adaptation","score":0.9919999837875366},{"id":"https://openalex.org/keywords/machine-translation","display_name":"machine translation","score":0.9729999899864197},{"id":"https://openalex.org/keywords/out-of-vocabulary-words","display_name":"out-of-vocabulary words","score":0.9300000071525574},{"id":"https://openalex.org/keywords/unseen-words","display_name":"unseen words","score":0.7409999966621399},{"id":"https://openalex.org/keywords/comparable-corpora","display_name":"comparable corpora","score":0.9760000109672546},{"id":"https://openalex.org/keywords/phrase-based-translation","display_name":"phrase-based translation","score":0.8980000019073486},{"id":"https://openalex.org/keywords/translation-errors","display_name":"translation errors","score":0.3569999933242798},{"id":"https://openalex.org/keywords/low-resource-language-translation","display_name":"low-resource translation","score":0.382999986410141}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8414187431335449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8151099681854248},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7137085795402527},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7073006629943848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7047756314277649},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6939871907234192},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5929055213928223},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5401079058647156},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.5137108564376831},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5015318393707275},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.45643460750579834},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.4423680603504181},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33154529333114624},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07610198855400085},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.05020934343338013},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.207.6219","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.207.6219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology-new/P/P11/P11-2071.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.221.245","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.221.245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal3.name/docs/daume11lexicaladapt.pdf","raw_type":"text"},{"id":"mag:2172268343","doi":null,"is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/P11-2071.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Meeting of the Association for Computational Linguistics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1997859518","https://openalex.org/W2025341678","https://openalex.org/W2101105183","https://openalex.org/W2105891181","https://openalex.org/W2116042738","https://openalex.org/W2122270629","https://openalex.org/W2123301721","https://openalex.org/W2124807415","https://openalex.org/W2137387514","https://openalex.org/W2139688603","https://openalex.org/W2140406733","https://openalex.org/W2171119909","https://openalex.org/W2356613612"],"related_works":["https://openalex.org/W2793879678","https://openalex.org/W2978664055","https://openalex.org/W7100631511","https://openalex.org/W7099195404","https://openalex.org/W2754727417","https://openalex.org/W2185701500","https://openalex.org/W2547182288","https://openalex.org/W2793214147","https://openalex.org/W2775767017","https://openalex.org/W6911515889"],"abstract_inverted_index":{"We":[0,46],"show":[1,47],"that":[2],"unseen":[3],"words":[4],"account":[5],"for":[6,42],"a":[7,23,55],"large":[8],"part":[9],"of":[10,22],"the":[11],"translation":[12,57],"error":[13],"when":[14],"moving":[15],"to":[16,26,39,50],"new":[17],"domains.":[18],"Using":[19],"an":[20],"extension":[21],"recent":[24],"approach":[25],"mining":[27],"translations":[28,41,53,63],"from":[29],"comparable":[30],"corpora":[31],"(Haghighi":[32],"et":[33],"al.,":[34],"2008),":[35],"we":[36],"are":[37],"able":[38],"find":[40],"otherwise":[43],"OOV":[44],"terms.":[45],"several":[48],"approaches":[49],"integrating":[51],"such":[52],"into":[54],"phrasebased":[56],"system,":[58],"yielding":[59],"consistent":[60],"improvements":[61],"in":[62],"quality":[64],"(between":[65],"0.5":[66],"and":[67,74],"1.5":[68],"Bleu":[69],"points)":[70],"on":[71],"four":[72],"domains":[73],"two":[75],"language":[76],"pairs.":[77],"1":[78]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":18},{"year":2014,"cited_by_count":20},{"year":2013,"cited_by_count":27},{"year":2012,"cited_by_count":11}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}
