{"id":"https://openalex.org/W4205400596","doi":"https://doi.org/10.1109/rivf51545.2021.9642071","title":"Improve Quora Question Pair Dataset for Question Similarity Task","display_name":"Improve Quora Question Pair Dataset for Question Similarity Task","publication_year":2021,"publication_date":"2021-08-19","ids":{"openalex":"https://openalex.org/W4205400596","doi":"https://doi.org/10.1109/rivf51545.2021.9642071"},"language":"en","primary_location":{"id":"doi:10.1109/rivf51545.2021.9642071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf51545.2021.9642071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 RIVF International Conference on Computing and Communication Technologies (RIVF)","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/A5103726616","display_name":"Huong Thi Thanh Le","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Huong T. Le","raw_affiliation_strings":["Hanoi University of Science and Technology,School of Information and Communication Technology,Hanoi,Vietnam","School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology,School of Information and Communication Technology,Hanoi,Vietnam","institution_ids":["https://openalex.org/I94518387"]},{"raw_affiliation_string":"School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066357943","display_name":"Dung Thi Phuong Cao","orcid":"https://orcid.org/0000-0003-2941-8593"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Dung T. Cao","raw_affiliation_strings":["Hanoi University of Science and Technology,School of Information and Communication Technology,Hanoi,Vietnam","School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology,School of Information and Communication Technology,Hanoi,Vietnam","institution_ids":["https://openalex.org/I94518387"]},{"raw_affiliation_string":"School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113663962","display_name":"Trung Bui","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trung H. Bui","raw_affiliation_strings":["Adobe Research,San Jose,California,USA","Adobe Research, San Jose, California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research,San Jose,California,USA","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"Adobe Research, San Jose, California, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024139615","display_name":"Long T. Luong","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Long T. Luong","raw_affiliation_strings":["Hanoi University of Science and Technology,School of Information and Communication Technology,Hanoi,Vietnam","School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology,School of Information and Communication Technology,Hanoi,Vietnam","institution_ids":["https://openalex.org/I94518387"]},{"raw_affiliation_string":"School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110832676","display_name":"Huy Quoc Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Huy Q. Nguyen","raw_affiliation_strings":["Hanoi University of Science and Technology,School of Information and Communication Technology,Hanoi,Vietnam","School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology,School of Information and Communication Technology,Hanoi,Vietnam","institution_ids":["https://openalex.org/I94518387"]},{"raw_affiliation_string":"School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9795,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.81382548,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9991999864578247,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9768999814987183,"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":0.7993861436843872},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7908892035484314},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7137497067451477},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6575562357902527},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5728644132614136},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5619429349899292},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5080146789550781},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46186310052871704},{"id":"https://openalex.org/keywords/competition","display_name":"Competition (biology)","score":0.4484717845916748},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4179684817790985}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7993861436843872},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7908892035484314},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7137497067451477},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6575562357902527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5728644132614136},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5619429349899292},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5080146789550781},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46186310052871704},{"id":"https://openalex.org/C91306197","wikidata":"https://www.wikidata.org/wiki/Q45767","display_name":"Competition (biology)","level":2,"score":0.4484717845916748},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4179684817790985},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rivf51545.2021.9642071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf51545.2021.9642071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 RIVF International Conference on Computing and Communication Technologies (RIVF)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307786","display_name":"Adobe Systems","ror":"https://ror.org/059tvcg64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2251558607","https://openalex.org/W2342901387","https://openalex.org/W2896457183","https://openalex.org/W3049545624","https://openalex.org/W4239510810","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2115758952","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W4212839359","https://openalex.org/W4288102755"],"abstract_inverted_index":{"Automatic":[0],"detection":[1],"of":[2,9,48,78],"semantically":[3],"equivalent":[4],"questions":[5],"is":[6],"a":[7,14],"task":[8,47],"the":[10,25,42,46,53,76,79],"utmost":[11],"importance":[12],"in":[13,24,44],"question":[15],"answering":[16],"system.":[17],"The":[18],"Quora":[19,26,80],"dataset,":[20],"which":[21],"was":[22],"released":[23],"Question":[27],"Pairs":[28],"competition":[29],"organized":[30],"by":[31,37,82,93],"Kaggle,":[32],"has":[33],"now":[34],"been":[35],"used":[36],"many":[38],"researches":[39],"to":[40],"train":[41],"system":[43],"solving":[45],"identifying":[49],"duplicate":[50],"questions.":[51],"However,":[52],"ground":[54],"truth":[55],"labels":[56,92],"on":[57,74,87],"this":[58,70],"dataset":[59,81],"are":[60],"not":[61],"100%":[62],"accurate":[63],"and":[64,90],"may":[65],"include":[66],"incorrect":[67],"labeling.":[68],"In":[69],"paper,":[71],"we":[72],"concentrate":[73],"improving":[75],"quality":[77],"combining":[83],"several":[84],"strategies,":[85],"basing":[86],"Bert,":[88],"rules,":[89],"reassigning":[91],"humans.":[94]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
