{"id":"https://openalex.org/W4396882328","doi":"https://doi.org/10.1145/3626772.3657869","title":"ProCIS: A Benchmark for Proactive Retrieval in Conversations","display_name":"ProCIS: A Benchmark for Proactive Retrieval in Conversations","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4396882328","doi":"https://doi.org/10.1145/3626772.3657869"},"language":"en","primary_location":{"id":"doi:10.1145/3626772.3657869","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657869","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626772.3657869?download=true","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th 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":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3626772.3657869?download=true","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015911813","display_name":"Chris Samarinas","orcid":"https://orcid.org/0000-0002-1941-3310"},"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":"Chris Samarinas","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA","University of Massachusetts Amherst Amherst, MA, United States"],"raw_orcid":"https://orcid.org/0000-0002-1941-3310","affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts Amherst Amherst, MA, United States","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101457713","display_name":"Hamed Zamani","orcid":"https://orcid.org/0000-0002-0800-3340"},"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 Zamani","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA","University of Massachusetts Amherst Amherst, MA, United States"],"raw_orcid":"https://orcid.org/0000-0002-0800-3340","affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts Amherst Amherst, MA, United States","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":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"830","last_page":"840"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9944000244140625,"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":0.9890000224113464,"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":0.7831869721412659},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7347643971443176},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40732213854789734},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36025822162628174},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3266659080982208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7831869721412659},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7347643971443176},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40732213854789734},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36025822162628174},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3266659080982208},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3626772.3657869","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657869","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626772.3657869?download=true","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2405.06460","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.06460","pdf_url":"https://arxiv.org/pdf/2405.06460","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3626772.3657869","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657869","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626772.3657869?download=true","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5}],"awards":[{"id":"https://openalex.org/G1462908608","display_name":"CAREER: Enriching Conversational Information Retrieval via Mixed-Initiative Interactions","funder_award_id":"2143434","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6128554767","display_name":null,"funder_award_id":"N000142212688","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6509441542","display_name":null,"funder_award_id":"N000142212688","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396882328.pdf","grobid_xml":"https://content.openalex.org/works/W4396882328.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1497613135","https://openalex.org/W2590822507","https://openalex.org/W2593527188","https://openalex.org/W2788125477","https://openalex.org/W2790000293","https://openalex.org/W2798328441","https://openalex.org/W2808352493","https://openalex.org/W2888302696","https://openalex.org/W2955157382","https://openalex.org/W2963033005","https://openalex.org/W2964223283","https://openalex.org/W2999905431","https://openalex.org/W3003611599","https://openalex.org/W3021397474","https://openalex.org/W3034654340","https://openalex.org/W3034920311","https://openalex.org/W3094347401","https://openalex.org/W3099944244","https://openalex.org/W3123634430","https://openalex.org/W3154280800","https://openalex.org/W3154898636","https://openalex.org/W3201646979","https://openalex.org/W3209431991","https://openalex.org/W4212975704","https://openalex.org/W4321485075","https://openalex.org/W4385642073","https://openalex.org/W4385688415","https://openalex.org/W4396723267"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W2087343574"],"abstract_inverted_index":{"The":[0],"field":[1],"of":[2,100,128,165],"conversational":[3,36,59,190],"information":[4,37,60,191],"seeking,":[5],"which":[6],"is":[7,16],"rapidly":[8],"gaining":[9],"interest":[10],"in":[11,54,73],"both":[12],"academia":[13],"and":[14,30,56,70,84,112,156],"industry,":[15],"changing":[17],"how":[18],"we":[19,89,171],"interact":[20],"with":[21],"search":[22],"engines":[23],"through":[24,117],"natural":[25],"language":[26],"interactions.":[27],"Existing":[28],"datasets":[29],"methods":[31],"are":[32,132],"mostly":[33],"evaluating":[34,57,153],"reactive":[35],"seeking":[38,61,192],"systems":[39,62],"that":[40,63,98,131,178],"solely":[41],"provide":[42,158],"response":[43],"to":[44,109,125,134,139],"every":[45],"query":[46],"from":[47],"the":[48,74,126,129,179,185],"user.":[49],"We":[50,105,120,144,176],"identify":[51],"a":[52,66,91,162,168],"gap":[53],"building":[55],"proactive":[58,95,141,147,189],"can":[64],"monitor":[65],"multi-party":[67],"human":[68],"conversation":[69,75,130],"proactively":[71],"engage":[72],"at":[76],"an":[77],"opportune":[78],"moment":[79],"by":[80],"retrieving":[81],"useful":[82],"resources":[83],"suggestions.":[85],"In":[86],"this":[87,174],"paper,":[88],"introduce":[90,145],"large-scale":[92],"dataset":[93],"for":[94,152,161,173],"document":[96],"retrieval":[97,142],"consists":[99],"over":[101],"2.8":[102],"million":[103],"conversations.":[104],"conduct":[106],"crowdsourcing":[107],"experiments":[108],"obtain":[110],"high-quality":[111],"relatively":[113],"complete":[114],"relevance":[115],"judgments":[116],"depth-k":[118],"pooling.":[119],"also":[121],"collect":[122],"annotations":[123],"related":[124,133],"parts":[127],"each":[135],"document,":[136],"enabling":[137],"us":[138],"evaluate":[140],"systems.":[143,193],"normalized":[146],"discounted":[148],"cumulative":[149],"gain":[150],"(npDCG)":[151],"these":[154],"systems,":[155],"further":[157],"benchmark":[159],"results":[160],"wide":[163],"range":[164],"models,":[166],"including":[167],"novel":[169],"model":[170],"developed":[172,180],"task.":[175],"believe":[177],"dataset,":[181],"called":[182],"ProCIS,":[183],"paves":[184],"path":[186],"towards":[187],"developing":[188]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}