{"id":"https://openalex.org/W2394530649","doi":"https://doi.org/10.21437/interspeech.2011-554","title":"A scalable approach to building a parallel corpus from the web","display_name":"A scalable approach to building a parallel corpus from the web","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2394530649","doi":"https://doi.org/10.21437/interspeech.2011-554","mag":"2394530649"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-554","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5112911746","display_name":"Vivek Kumar Rangarajan Sridhar","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Vivek Kumar Rangarajan Sridhar","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000683692","display_name":"Luciano Barbosa","orcid":"https://orcid.org/0000-0002-6858-4773"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luciano Barbosa","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111475783","display_name":"Srinivas Bangalore","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srinivas Bangalore","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112911746"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4206,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.93205546,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2113","last_page":"2116"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.996999979019165,"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":0.8511741757392883},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.8466168642044067},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.7914658784866333},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6536994576454163},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5956999659538269},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5812903046607971},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5351845622062683},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5191185474395752},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5087834000587463},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4718211591243744},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.4702543020248413},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4606914520263672},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3917040228843689},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09329670667648315}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8511741757392883},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8466168642044067},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7914658784866333},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6536994576454163},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5956999659538269},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5812903046607971},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5351845622062683},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5191185474395752},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5087834000587463},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4718211591243744},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.4702543020248413},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4606914520263672},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3917040228843689},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09329670667648315},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2011-554","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W103390042","https://openalex.org/W1522930108","https://openalex.org/W1733633583","https://openalex.org/W1928047241","https://openalex.org/W2047295649","https://openalex.org/W2070150502","https://openalex.org/W2101096097","https://openalex.org/W2101105183","https://openalex.org/W2101877405","https://openalex.org/W2107695330","https://openalex.org/W2116713744","https://openalex.org/W2124807415","https://openalex.org/W2146574666","https://openalex.org/W2148141553","https://openalex.org/W2149327368","https://openalex.org/W2151626491","https://openalex.org/W2156985047","https://openalex.org/W2758884106"],"related_works":["https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2026132847","https://openalex.org/W2137810919","https://openalex.org/W2964752624","https://openalex.org/W4255854114","https://openalex.org/W2026661369","https://openalex.org/W4385695127"],"abstract_inverted_index":{"Parallel":[0],"text":[1,83,146],"acquisition":[2],"from":[3,86,94,102],"the":[4,56,60,63,70,87,95,103,127,133,139,172],"Web":[5,37,52,91],"is":[6,30],"an":[7,165],"attractive":[8],"way":[9],"for":[10,26],"augmenting":[11],"statistical":[12],"models":[13],"(e.g.,":[14],"machine":[15,136],"translation,":[16],"crosslingual":[17],"document":[18,115],"retrieval)":[19],"with":[20],"domain":[21],"representative":[22],"data.":[23],"The":[24,144],"basis":[25],"obtaining":[27],"such":[28],"data":[29],"a":[31,46,75,120,155],"collection":[32,88,121],"of":[33,35,59,66,89,122,129,135,158],"pairs":[34],"bilingual":[36,51,67,90,123],"sites":[38,53,68,92],"or":[39],"pages.":[40],"In":[41],"this":[42],"work,":[43],"we":[44,73],"propose":[45],"crawling":[47,151],"strategy":[48,152],"that":[49,80,113],"locates":[50],"by":[54],"constraining":[55],"visitation":[57],"policy":[58],"crawler":[61],"to":[62,118],"graph":[64],"neighborhood":[65],"on":[69,171],"Web.":[71],"Subsequently,":[72],"use":[74],"novel":[76,150],"recursive":[77],"mining":[78],"technique":[79],"recursively":[81],"extracts":[82],"and":[84,141],"links":[85],"obtained":[93,147],"crawling.":[96],"Our":[97],"method":[98],"does":[99],"not":[100],"suffer":[101],"computationally":[104],"prohibitive":[105],"combinatorial":[106],"matching":[107],"typically":[108],"used":[109],"in":[110,132,138,154,160],"previous":[111],"work":[112],"uses":[114],"retrieval":[116],"techniques":[117],"match":[119],"webpages.":[124],"We":[125],"demonstrate":[126],"efficacy":[128],"our":[130,149],"approach":[131],"context":[134],"translation":[137,168],"tourism":[140],"hospitality":[142],"domain.":[143],"parallel":[145],"using":[148],"results":[153],"relative":[156],"improvement":[157],"21%":[159],"BLEU":[161],"score":[162],"(English-to-Spanish)":[163],"over":[164],"out-of-domain":[166],"seed":[167],"model":[169],"trained":[170],"European":[173],"parliamentary":[174],"proceedings.":[175]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
