{"id":"https://openalex.org/W3044795082","doi":"https://doi.org/10.1145/3397271.3401417","title":"Searching the Web for Cross-lingual Parallel Data","display_name":"Searching the Web for Cross-lingual Parallel Data","publication_year":2020,"publication_date":"2020-07-25","ids":{"openalex":"https://openalex.org/W3044795082","doi":"https://doi.org/10.1145/3397271.3401417","mag":"3044795082"},"language":"en","primary_location":{"id":"doi:10.1145/3397271.3401417","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401417","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-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/A5035119055","display_name":"Ahmed El-Kishky","orcid":"https://orcid.org/0000-0003-0121-7781"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ahmed El-Kishky","raw_affiliation_strings":["Facebook AI, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, Seattle, WA, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112315093","display_name":"Philipp Koehn","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":false,"raw_author_name":"Philipp Koehn","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015857371","display_name":"Holger Schwenk","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Holger Schwenk","raw_affiliation_strings":["Facebook AI, Paris, France"],"affiliations":[{"raw_affiliation_string":"Facebook AI, Paris, France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5035119055"],"corresponding_institution_ids":["https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":0.6628,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75773036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2417","last_page":"2420"},"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":0.9998999834060669,"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":0.9886000156402588,"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":0.8919171094894409},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6076870560646057},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5858873724937439},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.5770643353462219},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5727664232254028},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.538223385810852},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5324170589447021},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5101752281188965},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4312905967235565},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2729240655899048}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8919171094894409},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6076870560646057},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5858873724937439},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.5770643353462219},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5727664232254028},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.538223385810852},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5324170589447021},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5101752281188965},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4312905967235565},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2729240655899048}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3397271.3401417","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401417","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1834000468","https://openalex.org/W2016630033","https://openalex.org/W2029814127","https://openalex.org/W2032062380","https://openalex.org/W2041232209","https://openalex.org/W2079442239","https://openalex.org/W2085715652","https://openalex.org/W2102749417","https://openalex.org/W2107695330","https://openalex.org/W2145080939","https://openalex.org/W2148334774","https://openalex.org/W2251044566","https://openalex.org/W2339912288","https://openalex.org/W2425146075","https://openalex.org/W2496235729","https://openalex.org/W2511852057","https://openalex.org/W2773493195","https://openalex.org/W2787646045","https://openalex.org/W2839634574","https://openalex.org/W2903035303","https://openalex.org/W2963919854","https://openalex.org/W2970858854","https://openalex.org/W2973088264","https://openalex.org/W2977458338","https://openalex.org/W2986148666","https://openalex.org/W2998702515","https://openalex.org/W4302780227"],"related_works":["https://openalex.org/W2786253471","https://openalex.org/W3175595715","https://openalex.org/W4293584592","https://openalex.org/W2986030184","https://openalex.org/W2104907655","https://openalex.org/W4287212313","https://openalex.org/W2985215540","https://openalex.org/W3155572818","https://openalex.org/W3120880016","https://openalex.org/W2807849360"],"abstract_inverted_index":{"While":[0],"the":[1,62,67,83,171],"World":[2],"Wide":[3],"Web":[4,172],"provides":[5],"a":[6,30,34,79,92,121],"large":[7],"amount":[8],"of":[9,36,65],"text":[10,77,90],"in":[11,33,38,44],"many":[12],"languages,":[13],"cross-lingual":[14,27,47,57,71,88,103,180],"parallel":[15,26,70,76,89,104,134,165],"data":[16,28,105],"is":[17,85],"more":[18],"difficult":[19],"to":[20,86],"obtain.":[21],"Despite":[22],"its":[23],"scarcity,":[24],"this":[25,146],"plays":[29],"crucial":[31],"role":[32],"variety":[35],"tasks":[37],"natural":[39],"language":[40],"processing":[41],"with":[42],"applications":[43],"machine":[45,175],"translation,":[46],"information":[48],"retrieval,":[49],"and":[50,110,115,124,127,136,144,157,178],"document":[51],"classification,":[52],"as":[53,55,78,120,138,140],"well":[54,139],"learning":[56],"representations.":[58],"Here,":[59],"we":[60],"describe":[61,149],"end-to-end":[63],"process":[64],"searching":[66,101],"web":[68],"for":[69,100,102,132,142],"texts.":[72],"We":[73,97,113,148],"motivate":[74,114],"obtaining":[75],"retrieval":[80],"problem":[81],"whereby":[82],"goal":[84],"retrieve":[87],"from":[91,164,170],"large,":[93],"multilingual":[94,117],"web-crawled":[95],"corpus.":[96],"introduce":[98,116],"techniques":[99,126,141,156],"based":[106],"on":[107,161],"language,":[108],"content,":[109],"other":[111],"metadata.":[112],"sentence":[118],"embeddings":[119],"core":[122],"tool":[123],"demonstrate":[125],"models":[128,177],"that":[129],"leverage":[130],"them":[131],"identifying":[133],"documents":[135,168],"sentences":[137,162],"retrieving":[143],"filtering":[145],"data.":[147],"several":[150],"large-scale":[151],"datasets":[152],"curated":[153],"using":[154],"these":[155],"show":[158],"how":[159],"training":[160],"extracted":[163],"or":[166],"comparable":[167],"mined":[169],"can":[173],"improve":[174],"translation":[176],"facilitate":[179],"NLP.":[181]},"counts_by_year":[{"year":2021,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}