{"id":"https://openalex.org/W1508577659","doi":null,"title":"Combining Bilingual and Comparable Corpora for Low Resource Machine Translation","display_name":"Combining Bilingual and Comparable Corpora for Low Resource Machine Translation","publication_year":2013,"publication_date":"2013-08-01","ids":{"openalex":"https://openalex.org/W1508577659","mag":"1508577659"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.348.3939","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.348.3939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.jhu.edu/~anni/papers/irvineCCB_WMT13.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/A5011118385","display_name":"Ann Irvine","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ann Irvine","raw_affiliation_strings":["Johns Hopkins University, Baltimore, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068508539","display_name":"Chris Callison-Burch","orcid":"https://orcid.org/0000-0001-8196-1943","observed_orcids":["https://orcid.org/0000-0001-8196-1943"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Callison-Burch","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, United States"],"raw_orcid":"https://orcid.org/0000-0001-8196-1943","affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, United States","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.616,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.97243436,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"262","last_page":"270"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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":0.0003000000142492354,"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":0.00019999999494757503,"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/low-resource-language-translation","display_name":"low-resource translation","score":0.8510000109672546},{"id":"https://openalex.org/keywords/comparable-corpora","display_name":"comparable corpora","score":0.9110000133514404},{"id":"https://openalex.org/keywords/bilingual-lexicon-induction","display_name":"bilingual lexicon induction","score":0.9020000100135803},{"id":"https://openalex.org/keywords/phrase-based-machine-translation","display_name":"phrase-based statistical machine translation","score":0.8169999718666077},{"id":"https://openalex.org/keywords/feature-space-augmentation","display_name":"feature space augmentation","score":0.5090000033378601},{"id":"https://openalex.org/keywords/tamil","display_name":"Tamil language","score":0.8130000233650208},{"id":"https://openalex.org/keywords/telugu","display_name":"Telugu","score":1.0}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8653998374938965},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7938870191574097},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7561956644058228},{"id":"https://openalex.org/C2778756302","wikidata":"https://www.wikidata.org/wiki/Q8097","display_name":"Telugu","level":2,"score":0.721039354801178},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6772499084472656},{"id":"https://openalex.org/C2779662586","wikidata":"https://www.wikidata.org/wiki/Q36236","display_name":"Malayalam","level":2,"score":0.5860925912857056},{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.5310616493225098},{"id":"https://openalex.org/C519982507","wikidata":"https://www.wikidata.org/wiki/Q1568","display_name":"Hindi","level":2,"score":0.4857981204986572},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4829794466495514},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.4724322259426117},{"id":"https://openalex.org/C140688305","wikidata":"https://www.wikidata.org/wiki/Q5885","display_name":"Tamil","level":2,"score":0.471052885055542},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.45539751648902893},{"id":"https://openalex.org/C2779235283","wikidata":"https://www.wikidata.org/wiki/Q2640207","display_name":"Bilingual dictionary","level":2,"score":0.4450737237930298},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.42102983593940735},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.4119279980659485},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34771186113357544},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11841735243797302},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.348.3939","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.348.3939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.jhu.edu/~anni/papers/irvineCCB_WMT13.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.381.3486","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.381.3486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.jhu.edu/~ccb/publications/combining-bilingual-and-comparable-corpora.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.396.8650","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.396.8650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://wing.comp.nus.edu.sg/~antho/W/W13/W13-2233.pdf","raw_type":"text"},{"id":"mag:1508577659","doi":null,"is_oa":false,"landing_page_url":"https://aclweb.org/anthology/W/W13/W13-2233.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306421295","display_name":"Workshop on Statistical Machine Translation","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Workshop on Statistical Machine Translation","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W38126138","https://openalex.org/W170711724","https://openalex.org/W1966497645","https://openalex.org/W1973152633","https://openalex.org/W2033593667","https://openalex.org/W2041232209","https://openalex.org/W2041305041","https://openalex.org/W2072976288","https://openalex.org/W2101096097","https://openalex.org/W2102749417","https://openalex.org/W2103042430","https://openalex.org/W2105673178","https://openalex.org/W2119013622","https://openalex.org/W2121415745","https://openalex.org/W2121745180","https://openalex.org/W2124807415","https://openalex.org/W2130716237","https://openalex.org/W2139812240","https://openalex.org/W2140406733","https://openalex.org/W2140903445","https://openalex.org/W2144600658","https://openalex.org/W2144642230","https://openalex.org/W2152263452","https://openalex.org/W2153653739","https://openalex.org/W2159755860","https://openalex.org/W2163361328","https://openalex.org/W2168966090","https://openalex.org/W2169360026","https://openalex.org/W2170716095","https://openalex.org/W2172268343","https://openalex.org/W2250229103","https://openalex.org/W2282154246"],"related_works":["https://openalex.org/W2570764233","https://openalex.org/W7145069153","https://openalex.org/W574870997","https://openalex.org/W2153360668","https://openalex.org/W6908106033","https://openalex.org/W2769515885","https://openalex.org/W2425903306","https://openalex.org/W2185853379","https://openalex.org/W1973152633","https://openalex.org/W2137170544"],"abstract_inverted_index":{"Statistical":[0],"machine":[1],"translation":[2,84],"(SMT)":[3],"performance":[4],"suffers":[5],"when":[6],"models":[7,19],"are":[8],"trained":[9],"on":[10],"only":[11],"small":[12,53],"amounts":[13],"of":[14],"parallel":[15],"data.":[16],"The":[17],"learned":[18],"typically":[20],"have":[21],"both":[22],"low":[23,31],"accuracy":[24],"(incorrect":[25],"translations":[26,72],"and":[27,30,55,100],"feature":[28,81],"scores)":[29],"coverage":[32,62],"(high":[33],"out-of-vocabulary":[34],"rates).":[35],"In":[36],"this":[37],"work,":[38],"we":[39,60,77],"use":[40],"an":[41],"additional":[42],"data":[43],"resource,":[44],"comparable":[45,74,88],"corpora,":[46],"to":[47,69,92],"improve":[48,61,93],"both.":[49],"Beginning":[50],"with":[51,83],"a":[52],"bitext":[54],"corresponding":[56],"phrase-based":[57],"SMT":[58],"model,":[59],"by":[63],"using":[64],"bilingual":[65],"lexicon":[66],"induction":[67],"techniques":[68],"learn":[70],"new":[71],"from":[73],"corpora.":[75],"Then,":[76],"supplement":[78],"the":[79],"model\u2019s":[80],"space":[82],"scores":[85],"estimated":[86],"over":[87],"corpora":[89],"in":[90],"order":[91],"accuracy.":[94],"We":[95],"observe":[96],"improvements":[97],"between":[98],"0.5":[99],"1.7":[101],"BLEU":[102],"translating":[103],"Tamil,":[104],"Telugu,":[105]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}