{"id":"https://openalex.org/W2145080939","doi":"https://doi.org/10.3115/1034678.1034757","title":"Mining the Web for bilingual text","display_name":"Mining the Web for bilingual text","publication_year":1999,"publication_date":"1999-01-01","ids":{"openalex":"https://openalex.org/W2145080939","doi":"https://doi.org/10.3115/1034678.1034757","mag":"2145080939"},"language":"en","primary_location":{"id":"doi:10.3115/1034678.1034757","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034757","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034757","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics  -","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034757","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059946729","display_name":"Philip Resnik","orcid":"https://orcid.org/0000-0002-6130-8602"},"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":true,"raw_author_name":"Philip Resnik","raw_affiliation_strings":["University of Maryland, College Park, MD","University of Maryland  College Park MD"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland  College Park MD","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5059946729"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":18.7081,"has_fulltext":true,"cited_by_count":238,"citation_normalized_percentile":{"value":0.99330857,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"527","last_page":"534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9976999759674072,"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":0.9976999759674072,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9904000163078308,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9865000247955322,"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":0.8123846054077148},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6470282077789307},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5280659198760986},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5193066000938416},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.47948703169822693},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.44381818175315857},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.43095892667770386},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.43031075596809387},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.41880810260772705},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3291120231151581},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06972065567970276}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8123846054077148},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6470282077789307},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5280659198760986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5193066000938416},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.47948703169822693},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.44381818175315857},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.43095892667770386},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.43031075596809387},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.41880810260772705},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3291120231151581},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06972065567970276},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.3115/1034678.1034757","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034757","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034757","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics  -","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.13.2866","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.13.2866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/P/P99/P99-1068.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.34.4530","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.34.4530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.cs.umd.edu/pub/papers/papers/ncstrl.umcp/CS-TR-4153/CS-TR-4153.ps.Z","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.592.481","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.592.481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nlp.cs.swarthmore.edu/~richardw/papers/P99-1068.pdf","raw_type":"text"},{"id":"pmh:oai:acl.sr.language-archives.org:P99-1068","is_oa":false,"landing_page_url":"http://www.aclweb.org/anthology/P99-1068","pdf_url":null,"source":{"id":"https://openalex.org/S4306402137","display_name":"The COCOON platform (University of Paris)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102197404","host_organization_name":"Universit\u00e9 Paris-Sud","host_organization_lineage":["https://openalex.org/I102197404"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:americanae.aecid.es:3657165","is_oa":false,"landing_page_url":"http://americanae.aecid.es/americanae/es/registros/registro.do?tipoRegistro=MTD&idBib=3657165","pdf_url":null,"source":{"id":"https://openalex.org/S4306400786","display_name":"Americanae (AECID Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:drum.lib.umd.edu:1903/1084","is_oa":false,"landing_page_url":"http://hdl.handle.net/1903/1084","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Technical Report"}],"best_oa_location":{"id":"doi:10.3115/1034678.1034757","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034757","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034757","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics  -","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.800000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2145080939.pdf","grobid_xml":"https://content.openalex.org/works/W2145080939.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W119481552","https://openalex.org/W1489558200","https://openalex.org/W1608419360","https://openalex.org/W1636405317","https://openalex.org/W2097333193","https://openalex.org/W2153804780"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W141820298","https://openalex.org/W2049584446","https://openalex.org/W3151736118","https://openalex.org/W2079781215","https://openalex.org/W4378770497","https://openalex.org/W4362495644","https://openalex.org/W4308245303","https://openalex.org/W2883671469","https://openalex.org/W2728761353"],"abstract_inverted_index":{"STRAND":[0,25],"(Resnik,":[1],"1998)":[2],"is":[3,46],"a":[4],"language-independent":[5],"system":[6],"for":[7],"automatic":[8,29],"discovery":[9],"of":[10,36],"text":[11],"in":[12],"parallel":[13,50],"translation":[14],"on":[15],"the":[16,23],"World":[17],"Wide":[18],"Web.":[19],"This":[20],"paper":[21],"extends":[22],"preliminary":[24],"results":[26],"by":[27,34],"adding":[28],"language":[30],"identification,":[31],"scaling":[32],"up":[33],"orders":[35],"magnitude,":[37],"and":[38],"formally":[39],"evaluating":[40],"performance.":[41],"The":[42],"most":[43],"recent":[44],"end-product":[45],"an":[47],"automatically":[48],"acquired":[49],"corpus":[51],"comprising":[52],"2491":[53],"English-French":[54],"document":[55],"pairs,":[56],"approximately":[57],"1.5":[58],"million":[59],"words":[60],"per":[61],"language.":[62]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":11}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
