{"id":"https://openalex.org/W2951568144","doi":"https://doi.org/10.18653/v1/p19-1435","title":"Selection Bias Explorations and Debias Methods for Natural Language Sentence Matching Datasets","display_name":"Selection Bias Explorations and Debias Methods for Natural Language Sentence Matching Datasets","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2951568144","doi":"https://doi.org/10.18653/v1/p19-1435","mag":"2951568144"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1435","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1435","pdf_url":"https://www.aclweb.org/anthology/P19-1435.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1435.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100438476","display_name":"Guanhua Zhang","orcid":"https://orcid.org/0000-0003-1445-1817"},"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"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guanhua Zhang","raw_affiliation_strings":["Cloud and Smart Industries Group, Tencent, China","Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"Cloud and Smart Industries Group, Tencent, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090022501","display_name":"Bing Bai","orcid":"https://orcid.org/0000-0002-6953-1948"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Bai","raw_affiliation_strings":["Cloud and Smart Industries Group, Tencent, China"],"affiliations":[{"raw_affiliation_string":"Cloud and Smart Industries Group, Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112582835","display_name":"Jian Liang","orcid":"https://orcid.org/0000-0003-3890-1894"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Liang","raw_affiliation_strings":["Cloud and Smart Industries Group, Tencent, China"],"affiliations":[{"raw_affiliation_string":"Cloud and Smart Industries Group, Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102906188","display_name":"Kun Bai","orcid":"https://orcid.org/0000-0002-3773-5364"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Bai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112248869","display_name":"Shiyu Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Shiyu Chang","raw_affiliation_strings":["Cloud and Smart Industries Group, Tencent, China","MIT-IBM Watson AI Lab, IBM Research, USA"],"affiliations":[{"raw_affiliation_string":"Cloud and Smart Industries Group, Tencent, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"MIT-IBM Watson AI Lab, IBM Research, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101583277","display_name":"Mo Yu","orcid":"https://orcid.org/0000-0003-0949-6113"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mo Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102790470","display_name":"Conghui Zhu","orcid":"https://orcid.org/0000-0003-3132-3059"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Conghui Zhu","raw_affiliation_strings":["Harbin Institute of Technology, China","MIT-IBM Watson AI Lab, IBM Research, USA"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"MIT-IBM Watson AI Lab, IBM Research, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101661008","display_name":"Tiejun Zhao","orcid":"https://orcid.org/0000-0003-4659-4935"},"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":"Tiejun Zhao","raw_affiliation_strings":["Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100438476"],"corresponding_institution_ids":["https://openalex.org/I204983213","https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":3.99406138,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":{"value":0.94485629,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4418","last_page":"4429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7054337859153748},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6981154084205627},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6503035426139832},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.603594183921814},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5987555980682373},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.5832666158676147},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5630251169204712},{"id":"https://openalex.org/keywords/selection-bias","display_name":"Selection bias","score":0.5068057179450989},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4518640637397766},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.44338223338127136},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4330570697784424},{"id":"https://openalex.org/keywords/sampling-bias","display_name":"Sampling bias","score":0.4325892925262451},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1631891131401062},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13715064525604248}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7054337859153748},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6981154084205627},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6503035426139832},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.603594183921814},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5987555980682373},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.5832666158676147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5630251169204712},{"id":"https://openalex.org/C40423286","wikidata":"https://www.wikidata.org/wiki/Q284172","display_name":"Selection bias","level":2,"score":0.5068057179450989},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4518640637397766},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.44338223338127136},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4330570697784424},{"id":"https://openalex.org/C75917345","wikidata":"https://www.wikidata.org/wiki/Q2725298","display_name":"Sampling bias","level":3,"score":0.4325892925262451},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1631891131401062},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13715064525604248},{"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/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1435","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1435","pdf_url":"https://www.aclweb.org/anthology/P19-1435.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1435","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1435","pdf_url":"https://www.aclweb.org/anthology/P19-1435.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2951568144.pdf","grobid_xml":"https://content.openalex.org/works/W2951568144.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W658020064","https://openalex.org/W1535091708","https://openalex.org/W1548361610","https://openalex.org/W1836465849","https://openalex.org/W1840435438","https://openalex.org/W1980776243","https://openalex.org/W2007444087","https://openalex.org/W2025037675","https://openalex.org/W2031342017","https://openalex.org/W2032536435","https://openalex.org/W2037933327","https://openalex.org/W2044758663","https://openalex.org/W2095705004","https://openalex.org/W2098695000","https://openalex.org/W2101105183","https://openalex.org/W2121690051","https://openalex.org/W2150291618","https://openalex.org/W2154851992","https://openalex.org/W2250539671","https://openalex.org/W2250790822","https://openalex.org/W2280395961","https://openalex.org/W2306229986","https://openalex.org/W2340526403","https://openalex.org/W2402144811","https://openalex.org/W2437221155","https://openalex.org/W2507134384","https://openalex.org/W2593833795","https://openalex.org/W2756386045","https://openalex.org/W2769473018","https://openalex.org/W2791170418","https://openalex.org/W2889453388","https://openalex.org/W2896457183","https://openalex.org/W2944907732","https://openalex.org/W2953384591","https://openalex.org/W2962736243","https://openalex.org/W2962843521","https://openalex.org/W2962888238","https://openalex.org/W2963341956","https://openalex.org/W2963846996","https://openalex.org/W2964082993","https://openalex.org/W2964301648","https://openalex.org/W2969068412","https://openalex.org/W3102882112","https://openalex.org/W3104097132","https://openalex.org/W3197494818","https://openalex.org/W4232552111","https://openalex.org/W4232932184"],"related_works":["https://openalex.org/W3166594252","https://openalex.org/W1518030604","https://openalex.org/W2426976336","https://openalex.org/W2512741782","https://openalex.org/W2884844053","https://openalex.org/W3176915151","https://openalex.org/W1516084361","https://openalex.org/W4253047901","https://openalex.org/W4241973638","https://openalex.org/W2784801669"],"abstract_inverted_index":{"Natural":[0],"Language":[1],"Sentence":[2],"Matching":[3],"(NLSM)":[4],"has":[5],"gained":[6],"substantial":[7],"attention":[8],"from":[9],"both":[10],"academics":[11],"and":[12,15,37,56,91,111,126,150],"the":[13,31,46,54,71,85,88,94,102,131,139,144],"industry,":[14],"rich":[16],"public":[17],"datasets":[18,27,110],"contribute":[19],"a":[20,124],"lot":[21],"to":[22,129],"this":[23,57,98],"process.":[24],"However,":[25],"biased":[26],"can":[28,60,142],"also":[29],"hurt":[30],"generalization":[32,145],"performance":[33],"of":[34,51,87,104,116,147],"trained":[35,148],"models":[36],"give":[38,151],"untrustworthy":[39],"evaluation":[40,127,154],"results.":[41],"For":[42],"many":[43],"NLSM":[44,109],"datasets,":[45,55],"providers":[47],"select":[48],"some":[49,75],"pairs":[50],"sentences":[52],"into":[53],"sampling":[58],"procedure":[59],"easily":[61],"bring":[62],"unintended":[63],"pattern,":[64],"i.e.,":[65],"selection":[66,89,105],"bias.":[67,132],"One":[68],"example":[69],"is":[70],"QuoraQP":[72,136],"dataset,":[73],"where":[74],"content-independent":[76],"naive":[77],"features":[78,83],"are":[79,84,118],"unreasonably":[80],"predictive.":[81],"Such":[82],"reflection":[86],"bias":[90,106],"termed":[92],"as":[93],"\"leakage":[95],"features.\"":[96],"In":[97],"paper,":[99],"we":[100],"investigate":[101],"problem":[103],"on":[107,135],"six":[108],"find":[112],"that":[113,138],"four":[114],"out":[115],"them":[117],"significantly":[119],"biased.":[120],"We":[121],"further":[122],"propose":[123],"training":[125],"framework":[128,141],"alleviate":[130],"Experimental":[133],"results":[134,155],"suggest":[137],"proposed":[140],"improve":[143],"ability":[146],"models,":[149],"more":[152],"trustworthy":[153],"for":[156],"real-world":[157],"adoptions.":[158]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}