{"id":"https://openalex.org/W3021779606","doi":"https://doi.org/10.1145/3397271.3401262","title":"Expansion via Prediction of Importance with Contextualization","display_name":"Expansion via Prediction of Importance with Contextualization","publication_year":2020,"publication_date":"2020-07-25","ids":{"openalex":"https://openalex.org/W3021779606","doi":"https://doi.org/10.1145/3397271.3401262","mag":"3021779606"},"language":"en","primary_location":{"id":"doi:10.1145/3397271.3401262","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","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/2004.14245","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sean MacAvaney","orcid":null},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sean MacAvaney","raw_affiliation_strings":["Georgetown University, Washington, DC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgetown University, Washington, DC, USA","institution_ids":["https://openalex.org/I184565670"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Franco Maria Nardini","orcid":null},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Franco Maria Nardini","raw_affiliation_strings":["ISTI-CNR, Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ISTI-CNR, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Raffaele Perego","orcid":null},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Raffaele Perego","raw_affiliation_strings":["ISTI-CNR, Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ISTI-CNR, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nicola Tonellotto","orcid":null},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicola Tonellotto","raw_affiliation_strings":["University of Pisa, Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pisa, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nazli Goharian","orcid":null},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nazli Goharian","raw_affiliation_strings":["Georgetown University, Washington, DC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgetown University, Washington, DC, USA","institution_ids":["https://openalex.org/I184565670"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ophir Frieder","orcid":null},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ophir Frieder","raw_affiliation_strings":["Georgetown University, Washington, DC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgetown University, Washington, DC, USA","institution_ids":["https://openalex.org/I184565670"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1573","last_page":"1576"},"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":0.9991000294685364,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9983999729156494,"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/epic","display_name":"EPIC","score":0.566100001335144},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5482000112533569},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5424000024795532},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4652999937534332},{"id":"https://openalex.org/keywords/contextualization","display_name":"Contextualization","score":0.4528999924659729},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4438999891281128},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.4401000142097473},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4065999984741211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6736000180244446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5914000272750854},{"id":"https://openalex.org/C115519274","wikidata":"https://www.wikidata.org/wiki/Q267903","display_name":"EPIC","level":2,"score":0.566100001335144},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5482000112533569},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5424000024795532},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4652999937534332},{"id":"https://openalex.org/C2780712339","wikidata":"https://www.wikidata.org/wiki/Q5165204","display_name":"Contextualization","level":3,"score":0.4528999924659729},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4438999891281128},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.4401000142097473},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43050000071525574},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4065999984741211},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3935999870300293},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.38040000200271606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3711000084877014},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2953000068664551},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3397271.3401262","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2004.14245","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.14245","pdf_url":"https://arxiv.org/pdf/2004.14245","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},{"id":"pmh:oai:arpi.unipi.it:11568/1054903","is_oa":false,"landing_page_url":"http://hdl.handle.net/11568/1054903","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:dnet:people______::8519db6684a601779488a5935b4750c6","is_oa":true,"landing_page_url":"https://openportal.isti.cnr.it/doc?id=people______::8519db6684a601779488a5935b4750c6","pdf_url":null,"source":{"id":"https://openalex.org/S7407055261","display_name":"ISTI Open Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1573\u20131576, online, 25-30 July, 2020","raw_type":"http://purl.org/coar/resource_type/c_5794"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.14245","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.14245","pdf_url":"https://arxiv.org/pdf/2004.14245","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2899154813","https://openalex.org/W2940927814","https://openalex.org/W3001344098","https://openalex.org/W4205951122"],"related_works":[],"abstract_inverted_index":{"The":[0],"identification":[1],"of":[2,30,80,128],"relevance":[3],"with":[4,19,82,104,136,159],"little":[5],"textual":[6],"context":[7],"is":[8,102,150],"a":[9,20,34,125],"primary":[10],"challenge":[11],"in":[12,54,163],"passage":[13,40,119,133],"retrieval.":[14],"We":[15,72,84,96,144],"address":[16],"this":[17],"problem":[18],"representation-based":[21],"ranking":[22,120,134],"approach":[23,75],"that:":[24],"(1)":[25],"explicitly":[26],"models":[27],"the":[28,44,52,55,100,105,113,131,148],"importance":[29,45],"each":[31],"term":[32],"using":[33],"contextualized":[35],"language":[36],"model;":[37],"(2)":[38],"performs":[39],"expansion":[41,94],"by":[42,155],"propagating":[43],"to":[46,68,153],"similar":[47],"terms;":[48],"and":[49,92,117],"(3)":[50],"grounds":[51],"representations":[53,61],"lexicon,":[56],"making":[57],"them":[58],"interpretable.":[59],"Passage":[60],"can":[62],"be":[63],"pre-computed":[64],"at":[65],"index":[66],"time":[67],"reduce":[69],"query-time":[70],"latency.":[71],"call":[73],"our":[74],"EPIC":[76,87,123],"(Expansion":[77],"via":[78],"Prediction":[79],"Importance":[81],"Contextualization).":[83],"show":[85],"that":[86,99,147],"significantly":[88],"outperforms":[89],"prior":[90],"importance-modeling":[91],"document":[93,157],"approaches.":[95,121],"also":[97,145],"observe":[98],"performance":[101],"additive":[103],"current":[106],"leading":[107],"first-stage":[108],"retrieval":[109],"methods,":[110],"further":[111,151],"narrowing":[112],"gap":[114],"between":[115],"inexpensive":[116],"cost-prohibitive":[118],"Specifically,":[122],"achieves":[124],"[email":[126],"protected]":[127],"0.304":[129],"on":[130,141],"MS-MARCO":[132],"dataset":[135],"78ms":[137],"average":[138],"query":[139],"latency":[140,149],"commodity":[142],"hardware.":[143],"find":[146],"reduced":[152],"68ms":[154],"pruning":[156],"representations,":[158],"virtually":[160],"no":[161],"difference":[162],"effectiveness.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2020-05-13T00:00:00"}