{"id":"https://openalex.org/W2159712673","doi":"https://doi.org/10.3115/v1/w14-3357","title":"Using Comparable Corpora to Adapt MT Models to New Domains","display_name":"Using Comparable Corpora to Adapt MT Models to New Domains","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2159712673","doi":"https://doi.org/10.3115/v1/w14-3357","mag":"2159712673"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-3357","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-3357","pdf_url":"https://aclanthology.org/W14-3357.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 Ninth Workshop on Statistical Machine Translation","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W14-3357.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011118385","display_name":"Ann Irvine","orcid":null},"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":true,"raw_author_name":"Ann Irvine","raw_affiliation_strings":["Center for Language and Speech Processing Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing Johns Hopkins University","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"},"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":["Computer and Information Science Dept. University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"Computer and Information Science Dept. University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5011118385"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":2.96,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.92480246,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"437","last_page":"444"},"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":0.9997000098228455,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7093847393989563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3926265239715576},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38818058371543884}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7093847393989563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3926265239715576},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38818058371543884}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3115/v1/w14-3357","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-3357","pdf_url":"https://aclanthology.org/W14-3357.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 Ninth Workshop on Statistical Machine Translation","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.434.9704","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.434.9704","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_wmt14.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.458.1065","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.458.1065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cis.upenn.edu/~ccb/publications/using-comparable-corpora-for-mt-adaptation.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.675.5483","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.675.5483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aclweb.org/anthology/W/W14/W14-3357.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-3357","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-3357","pdf_url":"https://aclanthology.org/W14-3357.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 Ninth Workshop on Statistical Machine Translation","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7099999785423279}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310145","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2159712673.pdf","grobid_xml":"https://content.openalex.org/works/W2159712673.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W38126138","https://openalex.org/W265531733","https://openalex.org/W635530177","https://openalex.org/W1794756993","https://openalex.org/W1905522558","https://openalex.org/W1926502259","https://openalex.org/W1974967573","https://openalex.org/W2041232209","https://openalex.org/W2072976288","https://openalex.org/W2102749417","https://openalex.org/W2117278770","https://openalex.org/W2121415745","https://openalex.org/W2124807415","https://openalex.org/W2132001515","https://openalex.org/W2137387514","https://openalex.org/W2137698233","https://openalex.org/W2139812240","https://openalex.org/W2140406733","https://openalex.org/W2140460368","https://openalex.org/W2144600658","https://openalex.org/W2145662801","https://openalex.org/W2159755860","https://openalex.org/W2171119909","https://openalex.org/W2172268343","https://openalex.org/W2185701500","https://openalex.org/W2250229103","https://openalex.org/W2250695194","https://openalex.org/W2251202280","https://openalex.org/W2251302843","https://openalex.org/W2252053087","https://openalex.org/W2396575863","https://openalex.org/W2595715041","https://openalex.org/W4255764218","https://openalex.org/W4302780227"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655","https://openalex.org/W2359140296"],"abstract_inverted_index":{"In":[0,41],"previous":[1],"work":[2],"we":[3,44,58,65],"showed":[4],"that":[5,64],"when":[6],"using":[7,53],"an":[8],"SMT":[9],"model":[10,35,51,83],"trained":[11],"on":[12],"old-domain":[13],"data":[14,80],"to":[15,25,48,68,81,94],"translate":[16],"text":[17],"in":[18,103],"a":[19,69],"new-domain,":[20],"most":[21],"errors":[22,46],"are":[23],"due":[24,47],"unseen":[26,29],"source":[27],"words,":[28],"target":[30,45],"translations,":[31],"and":[32,85],"inaccurate":[33,49],"translation":[34,50],"scores":[36,52,98],"(Irvine":[37],"et":[38],"al.,":[39],"2013a).":[40],"this":[42],"work,":[43],"new-domain":[54,78,91],"comparable":[55,92],"corpora,":[56],"which":[57],"mine":[59],"from":[60],"Wikipedia.":[61],"We":[62,88],"assume":[63],"have":[66],"access":[67],"large":[70],"olddomain":[71],"parallel":[72,79],"training":[73],"corpus":[74],"but":[75],"only":[76],"enough":[77],"tune":[82],"parameters":[84],"do":[86],"evaluation.":[87],"use":[89],"the":[90,100],"corpora":[93],"estimate":[95],"additional":[96],"feature":[97],"over":[99],"phrase":[101],"pairs":[102],"our":[104],"baseline":[105],"models.":[106]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":6}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}