{"id":"https://openalex.org/W4416251638","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228792","title":"Be More Focused: A Key Information-Aware Framework with Text Reconstruction for Multi-Span Question Answering","display_name":"Be More Focused: A Key Information-Aware Framework with Text Reconstruction for Multi-Span Question Answering","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251638","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228792"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228792","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5100856773","display_name":"Lingai Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I1328775524","display_name":"Zhejiang Sci-Tech University","ror":"https://ror.org/03893we55","country_code":"CN","type":"education","lineage":["https://openalex.org/I1328775524"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lingai Jiang","raw_affiliation_strings":["Zhejiang Sci-Tech University,School of Computer Science and Technology,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Sci-Tech University,School of Computer Science and Technology,Hangzhou,China","institution_ids":["https://openalex.org/I1328775524"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077615805","display_name":"Zuohua Ding","orcid":"https://orcid.org/0000-0002-9671-7836"},"institutions":[{"id":"https://openalex.org/I1328775524","display_name":"Zhejiang Sci-Tech University","ror":"https://ror.org/03893we55","country_code":"CN","type":"education","lineage":["https://openalex.org/I1328775524"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuohua Ding","raw_affiliation_strings":["Zhejiang Sci-Tech University,School of Computer Science and Technology,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Sci-Tech University,School of Computer Science and Technology,Hangzhou,China","institution_ids":["https://openalex.org/I1328775524"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100856773"],"corresponding_institution_ids":["https://openalex.org/I1328775524"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1948462,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6775000095367432,"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":0.6775000095367432,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.15360000729560852,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.028999999165534973,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/key","display_name":"Key (lock)","score":0.8030999898910522},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6830000281333923},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6291999816894531},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5580000281333923},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.43369999527931213},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42489999532699585},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.39730000495910645},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3935000002384186}],"concepts":[{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.8030999898910522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79830002784729},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6830000281333923},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6291999816894531},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5580000281333923},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5551999807357788},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4406000077724457},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.43369999527931213},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42489999532699585},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.39730000495910645},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3743000030517578},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3644999861717224},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30149999260902405},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3005000054836273},{"id":"https://openalex.org/C45983554","wikidata":"https://www.wikidata.org/wiki/Q3412851","display_name":"Information quality","level":3,"score":0.2969000041484833},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.29089999198913574},{"id":"https://openalex.org/C178674793","wikidata":"https://www.wikidata.org/wiki/Q6031077","display_name":"Information filtering system","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28380000591278076},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.2563999891281128},{"id":"https://openalex.org/C2776543384","wikidata":"https://www.wikidata.org/wiki/Q593289","display_name":"Information access","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228792","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2912924812","https://openalex.org/W2963351448","https://openalex.org/W3034328552","https://openalex.org/W3098324846","https://openalex.org/W3100468923","https://openalex.org/W3114079967","https://openalex.org/W3203318855","https://openalex.org/W4287888456","https://openalex.org/W4382202848","https://openalex.org/W4385570851","https://openalex.org/W4387427108","https://openalex.org/W4387846571","https://openalex.org/W4388816657","https://openalex.org/W4391830542","https://openalex.org/W4396966254","https://openalex.org/W4404782885"],"related_works":[],"abstract_inverted_index":{"Multi-Span":[0],"Question":[1],"Answering":[2],"(MSQA)":[3],"has":[4],"gained":[5],"significant":[6,173],"attention":[7],"due":[8],"to":[9,12,38,82,95,103,158,192],"its":[10],"relevance":[11,125],"real-world":[13],"application":[14],"scenarios.":[15],"However,":[16],"key":[17,72,100,115,141],"information":[18,33,73,79,101,124,142],"is":[19],"often":[20],"concentrated":[21],"in":[22,50,143],"small":[23],"regions":[24],"of":[25,31,43,88,140],"the":[26,35,48,84,89,93,99,137,144,147,155,169,177,193],"context,":[27,91],"while":[28,105],"large":[29],"amounts":[30],"irrelevant":[32],"flood":[34],"input,":[36],"leading":[37],"an":[39,123],"excessively":[40],"high":[41],"proportion":[42],"negative":[44],"labels,":[45],"which":[46,75,120],"limits":[47],"model":[49,94],"locating":[51],"multi-span":[52,130],"answers":[53],"accurately.":[54],"To":[55],"alleviate":[56],"this":[57],"challenge,":[58],"we":[59,65,112],"propose":[60],"two":[61],"innovative":[62],"methods.":[63],"First,":[64],"design":[66],"a":[67,77,114,129],"text":[68],"reconstruction":[69],"technique":[70],"for":[71],"identification,":[74],"utilizes":[76],"multi-step":[78],"filtering":[80,107],"mechanism":[81],"optimize":[83],"quality":[85],"and":[86,146,160],"structure":[87],"input":[90],"enabling":[92],"focus":[96],"more":[97],"on":[98,176],"relevant":[102],"questions":[104],"effectively":[106],"out":[108],"noise":[109],"interference.":[110],"Second,":[111],"introduce":[113],"information-aware":[116],"joint":[117],"learning":[118],"framework,":[119],"jointly":[121],"trains":[122],"prediction":[126],"task":[127],"with":[128,180],"answer":[131,151],"extraction":[132],"task.":[133],"The":[134],"framework":[135],"captures":[136],"distribution":[138],"patterns":[139],"context":[145],"semantic":[148],"relationships":[149],"between":[150],"spans,":[152],"thereby":[153],"enhancing":[154],"model\u2019s":[156],"ability":[157],"understand":[159],"reason":[161],"over":[162],"complex":[163],"contexts.":[164],"Experimental":[165],"results":[166],"show":[167],"that":[168],"proposed":[170],"approach":[171],"achieves":[172],"performance":[174],"improvements":[175],"MultiSpanQA":[178],"dataset,":[179],"EM":[181],"F1":[182],"improving":[183],"by":[184],"3.07%-7.74%":[185],"across":[186],"different":[187],"pre-trained":[188],"language":[189],"models(PLMs)":[190],"compared":[191],"current":[194],"state-of-the-art(SOTA)":[195],"model.":[196]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}