{"id":"https://openalex.org/W4392904234","doi":"https://doi.org/10.1109/icassp48485.2024.10446388","title":"Theme-Enhanced Hard Negative Sample Mining for Open-Domain Question Answering","display_name":"Theme-Enhanced Hard Negative Sample Mining for Open-Domain Question Answering","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904234","doi":"https://doi.org/10.1109/icassp48485.2024.10446388"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446388","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5085268065","display_name":"Fulu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fulu Li","raw_affiliation_strings":["Central China Normal University,Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning School of Computer","Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning School of Computer, Central China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central China Normal University,Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning School of Computer","institution_ids":["https://openalex.org/I40963666"]},{"raw_affiliation_string":"Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning School of Computer, Central China Normal University","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101705596","display_name":"Zhiwen Xie","orcid":"https://orcid.org/0000-0003-0837-3285"},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwen Xie","raw_affiliation_strings":["Central China Normal University,Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning School of Computer","Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning School of Computer, Central China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central China Normal University,Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning School of Computer","institution_ids":["https://openalex.org/I40963666"]},{"raw_affiliation_string":"Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning School of Computer, Central China Normal University","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007102035","display_name":"Guangyou Zhou","orcid":"https://orcid.org/0000-0002-7675-6619"},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyou Zhou","raw_affiliation_strings":["Central China Normal University,Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning School of Computer","Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning School of Computer, Central China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central China Normal University,Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning School of Computer","institution_ids":["https://openalex.org/I40963666"]},{"raw_affiliation_string":"Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning School of Computer, Central China Normal University","institution_ids":["https://openalex.org/I40963666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I40963666"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12436","last_page":"12440"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","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/T11550","display_name":"Text and Document Classification Technologies","score":0.9865999817848206,"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":0.8401085138320923},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6116799116134644},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6079532504081726},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5769177079200745},{"id":"https://openalex.org/keywords/theme","display_name":"Theme (computing)","score":0.5363646149635315},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5090894103050232},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5080916881561279},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5067203640937805},{"id":"https://openalex.org/keywords/open-domain","display_name":"Open domain","score":0.47825729846954346},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4687528610229492},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4659477472305298},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4628414809703827},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.44297438859939575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4328470528125763},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37590914964675903},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1220579445362091},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07375693321228027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8401085138320923},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6116799116134644},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6079532504081726},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5769177079200745},{"id":"https://openalex.org/C33566652","wikidata":"https://www.wikidata.org/wiki/Q1065927","display_name":"Theme (computing)","level":2,"score":0.5363646149635315},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5090894103050232},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5080916881561279},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5067203640937805},{"id":"https://openalex.org/C2993776861","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Open domain","level":3,"score":0.47825729846954346},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4687528610229492},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4659477472305298},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4628414809703827},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.44297438859939575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4328470528125763},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37590914964675903},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1220579445362091},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07375693321228027},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446388","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2740321901","https://openalex.org/W2896457183","https://openalex.org/W2912924812","https://openalex.org/W2962985038","https://openalex.org/W2963339397","https://openalex.org/W3036320503","https://openalex.org/W3090114880","https://openalex.org/W3098468692","https://openalex.org/W3099700870","https://openalex.org/W3118999024","https://openalex.org/W3155895380","https://openalex.org/W3157758108","https://openalex.org/W3168875417","https://openalex.org/W4223609000","https://openalex.org/W4285270385","https://openalex.org/W4386092891","https://openalex.org/W6631190155","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6774222543","https://openalex.org/W6779872132","https://openalex.org/W6783961830","https://openalex.org/W6787757238","https://openalex.org/W6842169839"],"related_works":["https://openalex.org/W2391533720","https://openalex.org/W2951097643","https://openalex.org/W4309395021","https://openalex.org/W3091989500","https://openalex.org/W3215363805","https://openalex.org/W204133468","https://openalex.org/W2991310128","https://openalex.org/W4307481286","https://openalex.org/W2395174199","https://openalex.org/W4226441484"],"abstract_inverted_index":{"Dense":[0],"passage":[1],"retrieval":[2],"has":[3],"become":[4],"the":[5,9,24,36,59,79,83,116],"mainstream":[6],"method":[7,125],"in":[8],"first":[10],"stage":[11],"of":[12,27,35,75],"open-domain":[13,143],"question":[14],"answering,":[15],"which":[16],"usually":[17],"adopts":[18],"a":[19,104,121],"bi-encoder":[20],"structure":[21],"to":[22,41,53,108,115],"learn":[23],"dense":[25],"representation":[26],"questions":[28],"and":[29,63,65],"passages":[30],"for":[31,69,93,126],"semantic":[32],"matching.":[33],"One":[34],"main":[37],"challenges":[38],"currently":[39],"is":[40],"effectively":[42],"utilize":[43],"more":[44,129],"informative":[45],"hard":[46,71,95,110,131],"negatives.":[47,72],"Many":[48],"efforts":[49],"have":[50],"been":[51],"made":[52],"address":[54],"this":[55,87],"challenge":[56],"by":[57,134],"reducing":[58],"discrepancy":[60],"between":[61],"training":[62,66],"inference":[64],"expensive":[67],"cross-encoder":[68],"mining":[70],"However,":[73],"none":[74],"these":[76],"approaches":[77],"consider":[78],"theme":[80],"information":[81],"regarding":[82],"candidate":[84],"passages.":[85],"In":[86],"paper,":[88],"we":[89,102,119],"propose":[90],"an":[91],"approach":[92,107],"theme-enhanced":[94],"negative":[96,132],"sample":[97],"mining,":[98],"called":[99],"THNSM.":[100],"Firstly,":[101],"employ":[103],"topic":[105],"sampling":[106],"mine":[109],"negatives":[111],"that":[112,147],"are":[113],"related":[114],"topic.":[117],"Secondly,":[118],"introduce":[120],"straightforward":[122],"yet":[123],"effective":[124],"generating":[127],"even":[128],"challenging":[130],"samples":[133],"partially":[135],"fusing":[136],"their":[137],"features.":[138],"Empirical":[139],"results":[140],"on":[141],"popular":[142],"QA":[144],"datasets":[145],"demonstrate":[146],"THNSM":[148],"significantly":[149],"outperforms":[150],"previous":[151],"state-of-the-art":[152],"models.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}