{"id":"https://openalex.org/W3201188670","doi":"https://doi.org/10.1145/3459637.3482101","title":"Query-driven Segment Selection for Ranking Long Documents","display_name":"Query-driven Segment Selection for Ranking Long Documents","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3201188670","doi":"https://doi.org/10.1145/3459637.3482101","mag":"3201188670"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3482101","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2109.04611","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Youngwoo Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Youngwoo Kim","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Razieh Rahimi","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Razieh Rahimi","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hamed Bonab","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hamed Bonab","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":null,"display_name":"James Allan","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Allan","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":0.2931,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5324543,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3147","last_page":"3151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9988999962806702,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9988999962806702,"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/T10028","display_name":"Topic Modeling","score":0.9944999814033508,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/selection","display_name":"Selection (genetic algorithm)","score":0.6919999718666077},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6381999850273132},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5601999759674072},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4268999993801117},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3855000138282776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7512000203132629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6927000284194946},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6919999718666077},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6381999850273132},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5601999759674072},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4334999918937683},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4268999993801117},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35359999537467957},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27549999952316284},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.27549999952316284}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3459637.3482101","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2109.04611","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.04611","pdf_url":"https://arxiv.org/pdf/2109.04611","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2109.04611","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.04611","pdf_url":"https://arxiv.org/pdf/2109.04611","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6113990160","display_name":null,"funder_award_id":"IIS-1813662","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2940927814","https://openalex.org/W2945127593","https://openalex.org/W2970103342","https://openalex.org/W2971209824","https://openalex.org/W3021397474","https://openalex.org/W3044284384","https://openalex.org/W3104220682"],"related_works":[],"abstract_inverted_index":{"Transformer-based":[0],"rankers":[1,25],"have":[2],"shown":[3],"state-of-the-art":[4,118],"performance.":[5],"However,":[6,43],"their":[7],"self-attention":[8,122],"operation":[9],"is":[10,26],"mostly":[11],"unable":[12],"to":[13,22,27,66,86,116,135],"process":[14,125],"long":[15,64],"sequences.":[16,128],"One":[17],"of":[18,32,52],"the":[19,37,49,94,100,109,117],"common":[20],"approaches":[21],"train":[23],"these":[24,44],"heuristically":[28,110],"select":[29],"some":[30],"segments":[31,45],"each":[33],"document,":[34],"such":[35],"as":[36,40],"first":[38],"segment,":[39],"training":[41,68],"data.":[42,69],"may":[46],"not":[47],"contain":[48],"query-related":[50],"parts":[51],"documents.":[53],"To":[54],"address":[55],"this":[56],"problem,":[57],"we":[58],"propose":[59],"query-driven":[60],"segment":[61,71,102],"selection":[62],"from":[63],"documents":[65],"build":[67],"The":[70,89],"selector":[72,103],"provides":[73],"relevant":[74],"samples":[75,82],"with":[76,99,120],"more":[77],"accurate":[78],"labels":[79],"and":[80,113],"non-relevant":[81],"which":[83],"are":[84],"harder":[85],"be":[87],"predicted.":[88],"experimental":[90],"results":[91],"show":[92],"that":[93,106,123],"basic":[95],"BERT-based":[96],"ranker":[97],"trained":[98,107],"proposed":[101],"significantly":[104],"outperforms":[105],"by":[108],"selected":[111],"segments,":[112],"performs":[114],"equally":[115],"model":[119],"localized":[121],"can":[124],"longer":[126],"input":[127],"Our":[129],"findings":[130],"open":[131],"up":[132],"new":[133],"direction":[134],"design":[136],"efficient":[137],"transformer-based":[138],"rankers.":[139]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2021-09-27T00:00:00"}