{"id":"https://openalex.org/W2017138122","doi":"https://doi.org/10.1145/2095536.2095599","title":"New approach for collecting high quality parallel corpora from multilingual websites","display_name":"New approach for collecting high quality parallel corpora from multilingual websites","publication_year":2011,"publication_date":"2011-12-05","ids":{"openalex":"https://openalex.org/W2017138122","doi":"https://doi.org/10.1145/2095536.2095599","mag":"2017138122"},"language":"en","primary_location":{"id":"doi:10.1145/2095536.2095599","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2095536.2095599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Information Integration and Web-based Applications and Services","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/A5034046313","display_name":"Cong Phap Huynh","orcid":null},"institutions":[{"id":"https://openalex.org/I3129492623","display_name":"University of Da Nang","ror":"https://ror.org/03ecpp171","country_code":"VN","type":"education","lineage":["https://openalex.org/I3129492623"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Cong Phap Huynh","raw_affiliation_strings":["Danang University of Technology, Vietnam"],"affiliations":[{"raw_affiliation_string":"Danang University of Technology, Vietnam","institution_ids":["https://openalex.org/I3129492623"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5034046313"],"corresponding_institution_ids":["https://openalex.org/I3129492623"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.08349159,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"341","last_page":"344"},"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":0.9972000122070312,"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":0.9930999875068665,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8977140784263611},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.6758930683135986},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.629487931728363},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6094937324523926},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5899918079376221},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5764071345329285},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5388334393501282},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4579436182975769},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4579239785671234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4284963607788086},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4280412495136261},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3414139449596405},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1602497398853302}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8977140784263611},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.6758930683135986},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.629487931728363},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6094937324523926},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5899918079376221},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5764071345329285},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5388334393501282},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4579436182975769},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4579239785671234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4284963607788086},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4280412495136261},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3414139449596405},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1602497398853302},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2095536.2095599","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2095536.2095599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Information Integration and Web-based Applications and Services","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W4811149","https://openalex.org/W22168010","https://openalex.org/W1594603936","https://openalex.org/W2020498346","https://openalex.org/W2080254493","https://openalex.org/W2133531268","https://openalex.org/W2138553032","https://openalex.org/W2140903445","https://openalex.org/W2158652061","https://openalex.org/W2166606631","https://openalex.org/W2758884106","https://openalex.org/W4230872509","https://openalex.org/W6600880057"],"related_works":["https://openalex.org/W2786253471","https://openalex.org/W2990400634","https://openalex.org/W3175595715","https://openalex.org/W4293584592","https://openalex.org/W2986030184","https://openalex.org/W2104907655","https://openalex.org/W4287212313","https://openalex.org/W3155572818","https://openalex.org/W2985215540","https://openalex.org/W2963357083"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"a":[5,61,66],"new":[6],"approach":[7,31,59],"for":[8,32,37],"extracting":[9],"the":[10,26,30,38],"high":[11],"quality":[12,88],"(HQ)":[13],"parallel":[14,80,85],"corpora":[15,86],"from":[16],"multilingual":[17,77],"resources.":[18],"The":[19],"original":[20],"of":[21,68],"our":[22],"research":[23],"compared":[24],"to":[25,46,54,83],"previous":[27,43],"works":[28],"is":[29,60,89],"gaining":[33],"HQ":[34,56],"data":[35],"using":[36],"Machine":[39],"Translation":[40],"domain.":[41],"Almost":[42],"approaches":[44],"allowed":[45],"quickly":[47],"acquire":[48],"raw":[49],"corpora,":[50],"but":[51],"not":[52],"allow":[53],"gain":[55],"data.":[57],"Our":[58],"semi-automatic":[62],"process":[63],"including":[64],"in":[65],"serial":[67],"steps":[69],"that":[70],"can":[71],"automatically":[72],"detect":[73],"and":[74,79,93],"download":[75],"good":[76],"Websites":[78],"web":[81],"pages":[82],"construct":[84],"whose":[87],"well":[90],"validated,":[91],"revised,":[92],"enhanced":[94],"collaboratively.":[95]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
