{"id":"https://openalex.org/W4324266458","doi":"https://doi.org/10.1145/3579654.3579685","title":"Matching Long-form Document with Topic Extraction and Aggregation","display_name":"Matching Long-form Document with Topic Extraction and Aggregation","publication_year":2022,"publication_date":"2022-12-23","ids":{"openalex":"https://openalex.org/W4324266458","doi":"https://doi.org/10.1145/3579654.3579685"},"language":"en","primary_location":{"id":"doi:10.1145/3579654.3579685","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3579654.3579685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","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/A5058753258","display_name":"Hua Cai","orcid":"https://orcid.org/0000-0002-7738-129X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hua Cai","raw_affiliation_strings":["Algorithm Research Center, UniDT, China"],"affiliations":[{"raw_affiliation_string":"Algorithm Research Center, UniDT, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052912484","display_name":"Jingxi Hu","orcid":"https://orcid.org/0000-0003-4564-710X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingxi Hu","raw_affiliation_strings":["Algorithm Research Center, UniDT, China"],"affiliations":[{"raw_affiliation_string":"Algorithm Research Center, UniDT, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077938328","display_name":"Ren Ma","orcid":"https://orcid.org/0000-0002-6958-1443"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren Ma","raw_affiliation_strings":["Algorithm Research Center, UniDT, China"],"affiliations":[{"raw_affiliation_string":"Algorithm Research Center, UniDT, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016661410","display_name":"Yixiao Lu","orcid":"https://orcid.org/0000-0003-0540-6053"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yixiao Lu","raw_affiliation_strings":["Algorithm Research Center, UniDT, China"],"affiliations":[{"raw_affiliation_string":"Algorithm Research Center, UniDT, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015319602","display_name":"Qing Xu","orcid":"https://orcid.org/0000-0002-3747-3325"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qing Xu","raw_affiliation_strings":["Algorithm Research Center, UniDT, China"],"affiliations":[{"raw_affiliation_string":"Algorithm Research Center, UniDT, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5058753258"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18063011,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9977999925613403,"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":0.9883000254631042,"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":0.8411009907722473},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6647095084190369},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6372206211090088},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5956347584724426},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5502930283546448},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.504982054233551},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4741125702857971},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.4171954393386841},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4069386124610901},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38505077362060547},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37737464904785156}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8411009907722473},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6647095084190369},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6372206211090088},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5956347584724426},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5502930283546448},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.504982054233551},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4741125702857971},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.4171954393386841},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4069386124610901},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38505077362060547},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37737464904785156},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3579654.3579685","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3579654.3579685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G5187630019","display_name":null,"funder_award_id":"2021-GZL-RGZN-01020","funder_id":"https://openalex.org/F4320325413","funder_display_name":"Shanghai Municipal Commission of Economy and Informatization"}],"funders":[{"id":"https://openalex.org/F4320325413","display_name":"Shanghai Municipal Commission of Economy and Informatization","ror":"https://ror.org/04166ws88"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2131876387","https://openalex.org/W2178628967","https://openalex.org/W2265289447","https://openalex.org/W2470673105","https://openalex.org/W2539671052","https://openalex.org/W2593833795","https://openalex.org/W2911997761","https://openalex.org/W2979826702","https://openalex.org/W3124980712"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177","https://openalex.org/W2334580170"],"abstract_inverted_index":{"BERT-based":[0,146],"models":[1,174],"have":[2],"been":[3],"widely":[4],"used":[5],"for":[6,130],"document":[7,43,63,172],"matching,":[8],"but":[9],"they":[10],"generally":[11],"do":[12],"not":[13],"perform":[14],"well":[15],"on":[16,175],"the":[17,23,34,37,47,79,131,141,150,166],"matching":[18,51,64,128,158,173],"of":[19,31,40,49,73,81,97,133,145,153],"long-form":[20,42,62,154,171],"documents,":[21,155],"as":[22],"sequence":[24,142],"length":[25,143],"limitation":[26,144],"could":[27],"lead":[28],"to":[29,93,117,121],"loss":[30],"information":[32,124],"in":[33],"document.":[35],"Also,":[36],"increased":[38,151],"noise":[39,152],"a":[41,60,71,95,106,118,126],"would":[44],"further":[45],"complicate":[46],"capture":[48],"key":[50],"signals.":[52],"To":[53],"tackle":[54],"these":[55],"existing":[56],"problems,":[57],"we":[58,86],"propose":[59],"new":[61],"model,":[65,70],"named":[66],"EA-BERT.":[67],"In":[68,135],"this":[69,136],"set":[72],"topics":[74],"are":[75,114],"first":[76],"extracted":[77],"from":[78,90,160],"pair":[80,132],"documents.":[82,134],"For":[83],"each":[84],"topic,":[85],"gather":[87],"related":[88],"sentences":[89],"both":[91,176],"documents":[92],"form":[94],"\"bag":[96],"sentences\",":[98],"which":[99],"is":[100],"then":[101,115],"encoded":[102],"by":[103],"BERT":[104],"into":[105,125],"vector":[107],"containing":[108],"topic-level":[109,123],"information.":[110],"All":[111],"topic":[112],"vectors":[113],"passed":[116],"transformer":[119],"encoder":[120],"aggregate":[122],"document-level":[127,180],"result":[129],"way,":[137],"our":[138],"approach":[139],"overcomes":[140],"models,":[147],"filters":[148],"out":[149],"and":[156,178],"integrates":[157],"signals":[159],"multiple":[161],"topics.":[162],"Experiments":[163],"show":[164],"that":[165],"proposed":[167],"method":[168],"outperforms":[169],"current":[170],"Chinese":[177],"English":[179],"datasets.":[181]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}