{"id":"https://openalex.org/W2322902172","doi":null,"title":"Building a Large English-Chinese Parallel Corpus from Comparable Patents and its Experimental Application to SMT","display_name":"Building a Large English-Chinese Parallel Corpus from Comparable Patents and its Experimental Application to SMT","publication_year":2010,"publication_date":"2010-05-01","ids":{"openalex":"https://openalex.org/W2322902172","mag":"2322902172"},"language":"en","primary_location":{"id":"mag:2322902172","doi":null,"is_oa":false,"landing_page_url":"https://www.mt-archive.info/BUCC-2010-Lu.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5100715995","display_name":"Bin Lu","orcid":"https://orcid.org/0000-0002-7962-2333","observed_orcids":["https://orcid.org/0000-0002-7962-2333"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bin Lu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-7962-2333","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101889270","display_name":"Tao Jiang","orcid":"https://orcid.org/0009-0000-5359-4488","observed_orcids":["https://orcid.org/0009-0000-5359-4488"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Jiang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0000-5359-4488","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000121627","display_name":"Ka-Po Chow","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ka-Po Chow","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084139225","display_name":"Benjamin K. Tsou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benjamin K. Tsou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3222,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.92262798,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"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":0.9984999895095825,"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/T10759","display_name":"Translation Studies and Practices","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.00039999998989515007,"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/parallel-corpus-construction","display_name":"parallel corpus construction","score":0.7450000047683716},{"id":"https://openalex.org/keywords/comparable-corpora","display_name":"comparable corpora","score":0.781000018119812},{"id":"https://openalex.org/keywords/patent-claims","display_name":"patent claims","score":0.5630000233650208},{"id":"https://openalex.org/keywords/patent-abstracts","display_name":"patent abstracts","score":0.6570000052452087},{"id":"https://openalex.org/keywords/statistical-machine-translation","display_name":"statistical machine translation","score":0.843999981880188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7597460746765137},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7169768214225769},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7151204347610474},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6986601948738098},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.5998814105987549},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.583351731300354},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.455412894487381},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.14517903327941895},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0875171422958374},{"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/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2322902172","doi":null,"is_oa":false,"landing_page_url":"https://www.mt-archive.info/BUCC-2010-Lu.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W1489181569","https://openalex.org/W1491634991","https://openalex.org/W1498238796","https://openalex.org/W1509527650","https://openalex.org/W1543317902","https://openalex.org/W1819903106","https://openalex.org/W2006521203","https://openalex.org/W2006969979","https://openalex.org/W2047295649","https://openalex.org/W2097333193","https://openalex.org/W2104103102","https://openalex.org/W2107695330","https://openalex.org/W2111568449","https://openalex.org/W2117652747","https://openalex.org/W2119168550","https://openalex.org/W2124807415","https://openalex.org/W2146574666","https://openalex.org/W2148237806","https://openalex.org/W2152263452","https://openalex.org/W2152803722","https://openalex.org/W2156985047","https://openalex.org/W2168929382","https://openalex.org/W2437005631","https://openalex.org/W2758884106","https://openalex.org/W3202296894"],"related_works":["https://openalex.org/W7097058509","https://openalex.org/W2162583378","https://openalex.org/W1600642888","https://openalex.org/W2489538514","https://openalex.org/W7077527451","https://openalex.org/W3202296894","https://openalex.org/W2734597964","https://openalex.org/W6947093468","https://openalex.org/W2250876691","https://openalex.org/W2379087717"],"abstract_inverted_index":{"The":[0],"paper":[1],"provides":[2],"an":[3],"account":[4],"on":[5,48,94,136],"the":[6,37,44,84,90,101,119,140],"augmentation":[7],"of":[8,15,39,52,67],"a":[9,49,133],"Chinese-English":[10],"patent":[11,91],"parallel":[12,76,86,97],"corpus":[13,51,88],"consisting":[14],"about":[16,25],"160K":[17],"sentence":[18,33,61,87],"pairs,":[19],"which":[20,68,78,131],"has":[21],"been":[22,65],"enlarged":[23],"by":[24,36,116],"45":[26],"times":[27],"to":[28,79,128,138],"more":[29,56,71],"than":[30,57,72],"7":[31,73],"million":[32,59,74,96],"pairs":[34],"mostly":[35],"means":[38],"\u201charvesting\u201d":[40],"comparable":[41,54],"patents":[42],"from":[43,100],"Web.":[45],"First,":[46],"based":[47],"large":[50],"English-Chinese":[53],"patents,":[55],"22":[58],"bilingual":[60],"pair":[62],"candidates":[63],"have":[64],"mined,":[66],"we":[69],"extract":[70],"high-quality":[75],"sentences,":[77],"our":[80],"best":[81],"knowledge":[82],"is":[83],"largest":[85],"in":[89,144],"domain.":[92],"Based":[93],"1":[95],"sentences":[98],"extracted":[99],"abstract":[102],"and":[103,121],"claims":[104],"sections,":[105],"some":[106],"interesting":[107],"preliminary":[108],"SMT":[109],"results":[110],"are":[111],"also":[112],"reported":[113],"here.":[114],"Last":[115],"not":[117],"least,":[118],"method":[120],"approach":[122],"proposed":[123],"here":[124],"should":[125],"be":[126],"applicable":[127],"other":[129],"languages,":[130],"shows":[132],"novel":[134],"way":[135],"how":[137],"reduce":[139],"data":[141],"acquisition":[142],"bottleneck":[143],"multilingual":[145],"language":[146],"processing.":[147]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":2}],"updated_date":"2026-09-26T08:19:03.415552","created_date":"2016-06-24T00:00:00"}