{"id":"https://openalex.org/W3210939518","doi":"https://doi.org/10.1145/3459637.3481950","title":"SAUCE","display_name":"SAUCE","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3210939518","doi":"https://doi.org/10.1145/3459637.3481950","mag":"3210939518"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3481950","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3481950","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":["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/A5086474262","display_name":"Muntasir Wahed","orcid":"https://orcid.org/0000-0002-9948-023X"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muntasir Wahed","raw_affiliation_strings":["Virginia Tech, Blacksburg, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006397816","display_name":"Daniel Gruhl","orcid":"https://orcid.org/0009-0006-9124-6752"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Gruhl","raw_affiliation_strings":["IBM Research Almaden, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040505319","display_name":"Alfredo Alba","orcid":"https://orcid.org/0009-0002-7624-1364"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alfredo Alba","raw_affiliation_strings":["IBM Research Almaden, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045091443","display_name":"Anna Lisa Gentile","orcid":"https://orcid.org/0000-0002-6401-4175"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anna Lisa Gentile","raw_affiliation_strings":["IBM Research Almaden, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045816451","display_name":"Petar Ristoski","orcid":"https://orcid.org/0000-0002-1890-1507"},"institutions":[{"id":"https://openalex.org/I4210150719","display_name":"eBay (United States)","ror":"https://ror.org/05cnabr44","country_code":"US","type":"company","lineage":["https://openalex.org/I4210150719"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Petar Ristoski","raw_affiliation_strings":["eBay Inc, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"eBay Inc, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210150719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051321506","display_name":"Chad DeLuca","orcid":"https://orcid.org/0009-0009-7690-7454"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chad DeLuca","raw_affiliation_strings":["IBM Research Almaden, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108491986","display_name":"Steve Welch","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steve Welch","raw_affiliation_strings":["IBM Research Almaden, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043962698","display_name":"Ismini Lourentzou","orcid":"https://orcid.org/0000-0002-1238-772X"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ismini Lourentzou","raw_affiliation_strings":["Virginia Tech, Blacksburg, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15550937,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"4173","last_page":"4183"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9952999949455261,"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":0.831861138343811},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6324759125709534},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6311503648757935},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.630621612071991},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5753426551818848},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.573066234588623},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5099047422409058},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49938130378723145},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49188876152038574},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.4705249071121216},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06874629855155945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.831861138343811},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6324759125709534},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6311503648757935},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.630621612071991},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5753426551818848},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.573066234588623},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5099047422409058},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49938130378723145},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49188876152038574},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.4705249071121216},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06874629855155945},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3459637.3481950","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3481950","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1512387364","https://openalex.org/W1518577300","https://openalex.org/W1532325895","https://openalex.org/W1585731690","https://openalex.org/W1982242209","https://openalex.org/W2035432878","https://openalex.org/W2065347041","https://openalex.org/W2069270778","https://openalex.org/W2070996757","https://openalex.org/W2103296194","https://openalex.org/W2104987630","https://openalex.org/W2136189984","https://openalex.org/W2140095548","https://openalex.org/W2148540243","https://openalex.org/W2188138540","https://openalex.org/W2251390323","https://openalex.org/W2251759562","https://openalex.org/W2260244612","https://openalex.org/W2293997450","https://openalex.org/W2294798173","https://openalex.org/W2531638282","https://openalex.org/W2572960727","https://openalex.org/W2605035112","https://openalex.org/W2742124187","https://openalex.org/W2743327679","https://openalex.org/W2755833683","https://openalex.org/W2775002880","https://openalex.org/W2885194867","https://openalex.org/W2894375337","https://openalex.org/W2895715183","https://openalex.org/W2896457183","https://openalex.org/W2911489562","https://openalex.org/W2954142106","https://openalex.org/W2962762512","https://openalex.org/W2963213349","https://openalex.org/W2963469388","https://openalex.org/W2963602293","https://openalex.org/W2970641574","https://openalex.org/W2978017171","https://openalex.org/W2979826702","https://openalex.org/W2987154291","https://openalex.org/W2996776764","https://openalex.org/W2998216295","https://openalex.org/W3002145105","https://openalex.org/W3004011066","https://openalex.org/W3011585284","https://openalex.org/W3034238904","https://openalex.org/W3038572442","https://openalex.org/W3083092543","https://openalex.org/W3098903812","https://openalex.org/W3100788005","https://openalex.org/W3102679845","https://openalex.org/W3103250468","https://openalex.org/W3117527017","https://openalex.org/W4239019441","https://openalex.org/W4285719527","https://openalex.org/W4292779060","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W2487162673","https://openalex.org/W2793211469","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2942366970","https://openalex.org/W2011472225","https://openalex.org/W3000057026","https://openalex.org/W3048565508","https://openalex.org/W3163984363","https://openalex.org/W2327130486"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,72],"text":[3,13,44],"representation":[4],"have":[5],"shown":[6],"that":[7,77],"training":[8],"on":[9,90],"large":[10],"amounts":[11],"of":[12,26,42,53,114],"is":[14],"crucial":[15],"for":[16],"natural":[17],"language":[18],"understanding.":[19],"However,":[20],"models":[21],"trained":[22],"without":[23],"predefined":[24],"notions":[25],"topical":[27],"interest":[28],"typically":[29],"require":[30],"careful":[31],"fine-tuning":[32],"when":[33],"transferred":[34],"to":[35,98],"specialized":[36],"domains.":[37],"When":[38],"a":[39,50],"sufficient":[40],"amount":[41],"within-domain":[43],"may":[45],"not":[46],"be":[47],"available,":[48],"expanding":[49],"seed":[51,123],"corpus":[52,64],"relevant":[54],"documents":[55],"from":[56],"large-scale":[57],"web":[58,85],"data":[59],"poses":[60],"several":[61],"challenges.":[62],"First,":[63],"expansion":[65],"requires":[66],"scoring":[67],"and":[68,94],"ranking":[69],"each":[70],"document":[71],"the":[73,84,99,104,111],"collection,":[74],"an":[75],"operation":[76],"can":[78],"quickly":[79],"become":[80],"computationally":[81],"expensive":[82],"as":[83,103],"corpora":[86,124],"size":[87],"grows.":[88],"Relying":[89],"dense":[91],"vector":[92],"spaces":[93],"pairwise":[95],"similarity":[96],"adds":[97],"computational":[100],"expense.":[101],"Secondly,":[102],"domain":[105],"concept":[106],"becomes":[107,118],"more":[108],"nuanced,":[109],"capturing":[110],"long":[112],"tail":[113],"domain-specific":[115],"rare":[116],"terms":[117],"non-trivial,":[119],"especially":[120],"under":[121],"limited":[122],"scenarios.":[125]},"counts_by_year":[],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2021-11-08T00:00:00"}