{"id":"https://openalex.org/W4416016876","doi":"https://doi.org/10.1145/3746252.3761023","title":"SG-Filter: Enhancing Similar Text Retrieval via Hierarchical Summarized-Semantic Index and Adaptive Filtering","display_name":"SG-Filter: Enhancing Similar Text Retrieval via Hierarchical Summarized-Semantic Index and Adaptive Filtering","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416016876","doi":"https://doi.org/10.1145/3746252.3761023"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3761023","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","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/A5066342192","display_name":"J. Ye","orcid":"https://orcid.org/0009-0007-6189-3251"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiancai Ye","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058051415","display_name":"J Liu","orcid":"https://orcid.org/0009-0003-8280-9072"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Liu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038968284","display_name":"Haoyu Zhang","orcid":"https://orcid.org/0009-0003-3889-8688"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120301472","display_name":"Maojia Sheng","orcid":"https://orcid.org/0009-0009-8566-5135"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maojia Sheng","raw_affiliation_strings":["ByteDance, Beijing, China"],"affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106185520","display_name":"Tao Yang","orcid":"https://orcid.org/0009-0008-8195-5744"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Yang","raw_affiliation_strings":["ByteDance, Beijing, China"],"affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111878216","display_name":"Jianrong Xu","orcid":"https://orcid.org/0009-0000-7000-6537"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Xu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068894182","display_name":"Jinhao Li","orcid":"https://orcid.org/0009-0009-4286-6359"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhao Li","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100445061","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0001-6108-5157"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015946486","display_name":"Guohao Dai","orcid":"https://orcid.org/0000-0003-0849-3252"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guohao Dai","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China, Infinigence-AI, Shanghai, China, and Shanghai Innovation Institute, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China, Infinigence-AI, Shanghai, China, and Shanghai Innovation Institute, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5066342192"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4829932,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3866","last_page":"3876"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.85589998960495,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.85589998960495,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.04740000143647194,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.022299999371170998,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.6115999817848206},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6018999814987183},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5400999784469604},{"id":"https://openalex.org/keywords/recall-rate","display_name":"Recall rate","score":0.5205000042915344},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5117999911308289},{"id":"https://openalex.org/keywords/term-discrimination","display_name":"Term Discrimination","score":0.48820000886917114},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.4702000021934509}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7742999792098999},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.6115999817848206},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.609499990940094},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6018999814987183},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5400999784469604},{"id":"https://openalex.org/C2987098735","wikidata":"https://www.wikidata.org/wiki/Q3808900","display_name":"Recall rate","level":2,"score":0.5205000042915344},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5117999911308289},{"id":"https://openalex.org/C22639730","wikidata":"https://www.wikidata.org/wiki/Q7702546","display_name":"Term Discrimination","level":5,"score":0.48820000886917114},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.4702000021934509},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40689998865127563},{"id":"https://openalex.org/C178674793","wikidata":"https://www.wikidata.org/wiki/Q6031077","display_name":"Information filtering system","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C90288658","wikidata":"https://www.wikidata.org/wiki/Q3318149","display_name":"Human\u2013computer information retrieval","level":3,"score":0.32269999384880066},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3222000002861023},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2976999878883362},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C182861755","wikidata":"https://www.wikidata.org/wiki/Q5158391","display_name":"Concept search","level":4,"score":0.26820001006126404},{"id":"https://openalex.org/C78999398","wikidata":"https://www.wikidata.org/wiki/Q2899888","display_name":"Information needs","level":2,"score":0.259799987077713}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3761023","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1932742904","https://openalex.org/W2594090677","https://openalex.org/W2810583043","https://openalex.org/W2998702515","https://openalex.org/W3003627389","https://openalex.org/W3099700870","https://openalex.org/W3099977667","https://openalex.org/W3161820423","https://openalex.org/W3174809957","https://openalex.org/W4200629808","https://openalex.org/W4200635123","https://openalex.org/W4226325130","https://openalex.org/W4367046898","https://openalex.org/W4385571271","https://openalex.org/W4389520758","https://openalex.org/W4389921502","https://openalex.org/W4393152682","https://openalex.org/W4396823873","https://openalex.org/W4396843633","https://openalex.org/W4399114216","https://openalex.org/W4400531953","https://openalex.org/W4402670699","https://openalex.org/W4402671985","https://openalex.org/W4415124086"],"related_works":[],"abstract_inverted_index":{"Similar":[0],"Text":[1],"Retrieval":[2],"(STR)":[3],"is":[4,39,77,111],"an":[5],"essential":[6],"scenario":[7],"in":[8,27,118,155,160,165],"the":[9,23,47,55,65,80,93,97,101,106,115,121,152,156],"field":[10],"of":[11,34,50,83,96,123],"information":[12,49,62,72,82,89,125],"retrieval":[13,19],"(IR).":[14],"Unfortunately,":[15],"existing":[16,41,135],"mainstream":[17],"vector-based":[18],"methods":[20,136],"cannot":[21],"meet":[22],"recall":[24,32,116,166],"rate":[25,33,117],"requirements":[26],"STR":[28],"scenarios":[29],"(with":[30],"a":[31,142,161],"less":[35],"than":[36],"72%).":[37],"This":[38],"because":[40,120],"works":[42],"have":[43,141],"solely":[44],"focused":[45],"on":[46],"local":[48],"text":[51,56,84,102],"segments,":[52],"that":[53,78],"is,":[54],"segments":[57,85,103],"themselves":[58],"(":[59,69,86],"i.e.,":[60,70,87],"semantic":[61],")":[63,110],"and":[64,105],"relationships":[66],"between":[67,108],"them":[68],"structured":[71],").":[73],"Our":[74],"key":[75,94],"insight":[76],"utilizing":[79],"global":[81,153],"summarized":[88,124,138,157],"~.":[90],"It":[91],"includes":[92],"expression":[95],"documents":[98],"to":[99,127,149],"which":[100],"belong":[104],"relationship":[107,154],"documents.":[109],"crucial":[112],"for":[113],"improving":[114],"STR,":[119],"distinction":[122],"helps":[126],"filter":[128],"out":[129],"confusing":[130],"vectors":[131],"during":[132],"retrieval.":[133],"However,":[134],"using":[137],"info":[139],"still":[140],"critical":[143],"challenge.":[144],"Their":[145],"vectorization-based":[146],"approaches":[147],"fail":[148],"effectively":[150],"model":[151],"information,":[158],"resulting":[159],"further":[162],"79%":[163],"deterioration":[164],"rate.":[167]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-08T00:00:00"}