{"id":"https://openalex.org/W2145790509","doi":"https://doi.org/10.1145/1008992.1009002","title":"Building an information retrieval test collection for spontaneous conversational speech","display_name":"Building an information retrieval test collection for spontaneous conversational speech","publication_year":2004,"publication_date":"2004-07-25","ids":{"openalex":"https://openalex.org/W2145790509","doi":"https://doi.org/10.1145/1008992.1009002","mag":"2145790509"},"language":"en","primary_location":{"id":"doi:10.1145/1008992.1009002","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009002","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval","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/A5074322406","display_name":"Douglas W. Oard","orcid":"https://orcid.org/0000-0002-1696-0407"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Douglas W. Oard","raw_affiliation_strings":["University of Maryland, College Park, MD"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036787563","display_name":"Dagobert Soergel","orcid":"https://orcid.org/0000-0001-5806-2384"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dagobert Soergel","raw_affiliation_strings":["University of Maryland, College Park, MD"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003875781","display_name":"David Doermann","orcid":"https://orcid.org/0000-0003-1639-4561"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Doermann","raw_affiliation_strings":["University of Maryland, College Park, MD"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021878761","display_name":"Xiaoli Huang","orcid":"https://orcid.org/0000-0001-9628-5618"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoli Huang","raw_affiliation_strings":["University of Maryland, College Park, MD"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003561083","display_name":"Gabriel Murray","orcid":"https://orcid.org/0000-0003-2233-6288"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G. Craig Murray","raw_affiliation_strings":["University of Maryland, College Park, MD"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436355","display_name":"Jian\u2010qiang Wang","orcid":"https://orcid.org/0000-0001-7668-4881"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianqiang Wang","raw_affiliation_strings":["University of Maryland, College Park, MD"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY","IBM -- T. J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM -- T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071900309","display_name":"Martin Franz","orcid":"https://orcid.org/0000-0001-6697-3022"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Franz","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY","IBM -- T. J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM -- T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023304742","display_name":"Samuel Gustman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Gustman","raw_affiliation_strings":["Visual History Foundation, Los Angeles, CA"],"affiliations":[{"raw_affiliation_string":"Visual History Foundation, Los Angeles, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036270568","display_name":"James Mayfield","orcid":"https://orcid.org/0000-0003-3866-3013"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Mayfield","raw_affiliation_strings":["The Johns Hopkins University","The Johns Hopkins University ,"],"affiliations":[{"raw_affiliation_string":"The Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"The Johns Hopkins University ,","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052991227","display_name":"Liliya Kharevych","orcid":null},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liliya Kharevych","raw_affiliation_strings":["California Institute of Technology"],"affiliations":[{"raw_affiliation_string":"California Institute of Technology","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004510221","display_name":"Stephanie Strassel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114480","display_name":"Authorised Association Consortium","ror":"https://ror.org/01j5adv11","country_code":"TZ","type":"other","lineage":["https://openalex.org/I4210114480"]}],"countries":["TZ"],"is_corresponding":false,"raw_author_name":"Stephanie Strassel","raw_affiliation_strings":["Linguistic Data Consortium"],"affiliations":[{"raw_affiliation_string":"Linguistic Data Consortium","institution_ids":["https://openalex.org/I4210114480"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5074322406"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":10.7929,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.98285731,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9976000189781189,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9976000189781189,"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":0.9944000244140625,"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/T12031","display_name":"Speech and dialogue systems","score":0.9934999942779541,"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":0.814623236656189},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.7725839614868164},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7348124980926514},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7127930521965027},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.666232168674469},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.6489477157592773},{"id":"https://openalex.org/keywords/formative-assessment","display_name":"Formative assessment","score":0.6385273933410645},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.519749641418457},{"id":"https://openalex.org/keywords/relevance-feedback","display_name":"Relevance feedback","score":0.45600947737693787},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.4297626316547394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37332701683044434},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34390851855278015},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.10724186897277832},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07893460988998413}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.814623236656189},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.7725839614868164},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7348124980926514},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7127930521965027},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.666232168674469},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.6489477157592773},{"id":"https://openalex.org/C42525527","wikidata":"https://www.wikidata.org/wiki/Q1209955","display_name":"Formative assessment","level":2,"score":0.6385273933410645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.519749641418457},{"id":"https://openalex.org/C2779532271","wikidata":"https://www.wikidata.org/wiki/Q445558","display_name":"Relevance feedback","level":4,"score":0.45600947737693787},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.4297626316547394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37332701683044434},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34390851855278015},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.10724186897277832},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07893460988998413},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1008992.1009002","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009002","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310145","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95"},{"id":"https://openalex.org/F4320332169","display_name":"Directorate for Computer and Information Science and Engineering","ror":"https://ror.org/025kzpk63"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W48198363","https://openalex.org/W112383835","https://openalex.org/W210033121","https://openalex.org/W210770835","https://openalex.org/W1482214997","https://openalex.org/W1540719499","https://openalex.org/W1594112393","https://openalex.org/W1965690069","https://openalex.org/W1967998665","https://openalex.org/W1977986156","https://openalex.org/W1990420106","https://openalex.org/W1994960885","https://openalex.org/W1998291146","https://openalex.org/W2005422315","https://openalex.org/W2029852711","https://openalex.org/W2057495142","https://openalex.org/W2073722401","https://openalex.org/W2103584254","https://openalex.org/W2120308175","https://openalex.org/W2127923419","https://openalex.org/W2153804780","https://openalex.org/W2158195707","https://openalex.org/W2166637769","https://openalex.org/W2998461326","https://openalex.org/W4233760227","https://openalex.org/W4376490867"],"related_works":["https://openalex.org/W609482051","https://openalex.org/W3199325201","https://openalex.org/W2792035366","https://openalex.org/W4386050096","https://openalex.org/W2360976019","https://openalex.org/W2906881146","https://openalex.org/W2351166673","https://openalex.org/W2390109066","https://openalex.org/W2002537515","https://openalex.org/W2349355552"],"abstract_inverted_index":{"Test":[0],"collections":[1],"model":[2],"use":[3,18,117],"cases":[4],"in":[5,42],"ways":[6],"that":[7],"facilitate":[8],"evaluation":[9,104],"of":[10,19,30,45,78,118],"information":[11],"retrieval":[12,29,112],"systems.":[13],"This":[14],"paper":[15],"describes":[16],"the":[17,119],"search-guided":[20],"relevance":[21,80],"assessment":[22,96],"to":[23,82,101,115],"create":[24],"a":[25,76],"test":[26],"collection":[27],"for":[28,68,87,110],"spontaneous":[31],"conversational":[32],"speech.":[33],"Approximately":[34],"10,000":[35],"thematically":[36],"coherent":[37],"segments":[38,86],"were":[39,73],"manually":[40,56],"identified":[41],"625":[43],"hours":[44],"oral":[46],"history":[47],"interviews":[48],"with":[49],"246":[50],"individuals.":[51],"Automatic":[52],"speech":[53],"recognition":[54],"results,":[55],"prepared":[57],"summaries,":[58],"controlled":[59],"vocabulary":[60],"indexing,":[61],"and":[62],"name":[63],"authority":[64],"control":[65],"are":[66,113],"available":[67],"every":[69],"segment.":[70],"Those":[71],"features":[72],"leveraged":[74],"by":[75],"team":[77],"four":[79],"assessors":[81],"identify":[83],"topically":[84],"relevant":[85],"28":[88],"topics":[89],"developed":[90],"from":[91],"actual":[92],"user":[93],"requests.":[94],"Search-guided":[95],"yielded":[97],"sufficient":[98],"inter-annotator":[99],"agreement":[100],"support":[102],"formative":[103],"during":[105],"system":[106],"development.":[107],"Baseline":[108],"results":[109],"ranked":[111],"presented":[114],"illustrate":[116],"collection.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
