{"id":"https://openalex.org/W2889968917","doi":"https://doi.org/10.18653/v1/d18-1536","title":"The BQ Corpus: A Large-scale Domain-specific Chinese Corpus For Sentence Semantic Equivalence Identification","display_name":"The BQ Corpus: A Large-scale Domain-specific Chinese Corpus For Sentence Semantic Equivalence Identification","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2889968917","doi":"https://doi.org/10.18653/v1/d18-1536","mag":"2889968917"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1536","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1536","pdf_url":"https://www.aclweb.org/anthology/D18-1536.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1536.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101715379","display_name":"Chen Jing","orcid":"https://orcid.org/0009-0000-5614-0705"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Chen","raw_affiliation_strings":["Shenzhen Calligraphy Digital Simulation Technology Lab, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Calligraphy Digital Simulation Technology Lab, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101895423","display_name":"Qingcai Chen","orcid":"https://orcid.org/0000-0001-8473-7293"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingcai Chen","raw_affiliation_strings":["Shenzhen Calligraphy Digital Simulation Technology Lab, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Calligraphy Digital Simulation Technology Lab, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352321","display_name":"Xin Liu","orcid":"https://orcid.org/0000-0003-2802-594X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":["Shenzhen Calligraphy Digital Simulation Technology Lab, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Calligraphy Digital Simulation Technology Lab, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058675840","display_name":"Haijun Yang","orcid":"https://orcid.org/0000-0001-8941-7571"},"institutions":[{"id":"https://openalex.org/I4210138097","display_name":"Riverbank Local Redevelopment Authority","ror":"https://ror.org/04qz58m35","country_code":"US","type":"government","lineage":["https://openalex.org/I4210138097"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haijun Yang","raw_affiliation_strings":["WeBank Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WeBank Inc","institution_ids":["https://openalex.org/I4210138097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069216030","display_name":"Daohe Lu","orcid":"https://orcid.org/0009-0005-9916-3620"},"institutions":[{"id":"https://openalex.org/I4210138097","display_name":"Riverbank Local Redevelopment Authority","ror":"https://ror.org/04qz58m35","country_code":"US","type":"government","lineage":["https://openalex.org/I4210138097"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daohe Lu","raw_affiliation_strings":["WeBank Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WeBank Inc","institution_ids":["https://openalex.org/I4210138097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014238603","display_name":"Buzhou Tang","orcid":"https://orcid.org/0000-0003-0271-8246"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Buzhou Tang","raw_affiliation_strings":["Shenzhen Calligraphy Digital Simulation Technology Lab, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Calligraphy Digital Simulation Technology Lab, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":119,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4946","last_page":"4951"},"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9940000176429749,"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/natural-language-processing","display_name":"Natural language processing","score":0.8107642531394958},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.774163007736206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6559593677520752},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6038960218429565},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5924464464187622},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5266596674919128},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.5218785405158997},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5005707740783691},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.4877665638923645},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45945483446121216},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.42783066630363464},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4221370220184326},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3510001301765442},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24901434779167175}],"concepts":[{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.8107642531394958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.774163007736206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6559593677520752},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6038960218429565},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5924464464187622},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5266596674919128},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.5218785405158997},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5005707740783691},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.4877665638923645},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45945483446121216},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.42783066630363464},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4221370220184326},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3510001301765442},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24901434779167175},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d18-1536","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1536","pdf_url":"https://www.aclweb.org/anthology/D18-1536.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1536","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1536","pdf_url":"https://www.aclweb.org/anthology/D18-1536.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2060668466","display_name":null,"funder_award_id":"61473101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8496641075","display_name":null,"funder_award_id":"61573118","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W131533222","https://openalex.org/W658020064","https://openalex.org/W1514017746","https://openalex.org/W1566018662","https://openalex.org/W1832693441","https://openalex.org/W1980776243","https://openalex.org/W2079735306","https://openalex.org/W2101105183","https://openalex.org/W2153702313","https://openalex.org/W2159849140","https://openalex.org/W2165232124","https://openalex.org/W2170738476","https://openalex.org/W2280395961","https://openalex.org/W2294860948","https://openalex.org/W2593833795","https://openalex.org/W2612867916","https://openalex.org/W2756386045","https://openalex.org/W2951359136","https://openalex.org/W2962888238","https://openalex.org/W2963508788","https://openalex.org/W2963719234"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2578505095","https://openalex.org/W2348452562","https://openalex.org/W3163680058","https://openalex.org/W2251724625","https://openalex.org/W3183077996","https://openalex.org/W2625499837","https://openalex.org/W2806999834"],"abstract_inverted_index":{"This":[0],"paper":[1,45],"introduces":[2],"the":[3,56,60,64,72,83,89,97,108,132,141,144],"Bank":[4],"Question":[5],"(BQ)":[6],"corpus,":[7,127],"a":[8,39,47,159],"Chinese":[9,137,152],"corpus":[10,19,139,146,169],"for":[11,103,151,162],"sentence":[12],"semantic":[13,154],"equivalence":[14],"identification":[15],"(SSEI).":[16],"The":[17,168],"BQ":[18,145],"contains":[20],"120,000":[21],"question":[22,101,153],"pairs":[23,102],"from":[24,37],"1-year":[25],"online":[26],"bank":[27,142],"custom":[28],"service":[29],"logs.":[30],"To":[31],"efficiently":[32],"process":[33],"and":[34,99,112,164],"annotate":[35],"questions":[36,54,62,91],"such":[38],"large":[40],"scale":[41],"of":[42],"logs,":[43],"this":[44],"proposes":[46],"clustering":[48],"based":[49,77],"annotation":[50],"method":[51],"to":[52,87],"achieve":[53],"with":[55,63],"same":[57,65,109],"intent.":[58],"First,":[59],"deduplicated":[61],"answer":[66],"are":[67,85,105],"clustered":[68,90],"into":[69,92],"stacks":[70],"by":[71],"Word":[73],"Mover's":[74],"Distance":[75],"(WMD)":[76],"Affinity":[78],"Propagation":[79],"(AP)":[80],"algorithm.":[81],"Then,":[82],"annotators":[84],"asked":[86],"assign":[88],"different":[93,114],"intent":[94,110,115],"categories.":[95],"Finally,":[96],"positive":[98],"negative":[100],"SSEI":[104,122,138,166],"selected":[106],"in":[107,140,172],"category":[111],"between":[113],"categories":[116],"respectively.":[117],"We":[118],"also":[119,158],"present":[120],"six":[121],"benchmark":[123],"performance":[124],"on":[125],"our":[126],"including":[128],"state-of-the-art":[129],"algorithms.":[130],"As":[131],"largest":[133],"manually":[134],"annotated":[135],"public":[136,173],"domain,":[143],"is":[147,170],"not":[148],"only":[149],"useful":[150],"matching":[155],"research,":[156],"but":[157],"significant":[160],"resource":[161],"cross-lingual":[163],"crossdomain":[165],"research.":[167],"available":[171],"1":[174],".":[175]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}