{"id":"https://openalex.org/W3135630341","doi":"https://doi.org/10.1145/3437963.3441760","title":"Quotebank","display_name":"Quotebank","publication_year":2021,"publication_date":"2021-03-06","ids":{"openalex":"https://openalex.org/W3135630341","doi":"https://doi.org/10.1145/3437963.3441760","mag":"3135630341"},"language":"en","primary_location":{"id":"doi:10.1145/3437963.3441760","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3437963.3441760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/294900","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035586856","display_name":"Timot\u00e9 Vaucher","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Timot\u00e9 Vaucher","raw_affiliation_strings":["\u00c9cole polytechnique f\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"\u00c9cole polytechnique f\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018128415","display_name":"Andreas Spitz","orcid":"https://orcid.org/0000-0002-5282-6133"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andreas Spitz","raw_affiliation_strings":["\u00c9cole polytechnique f\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"\u00c9cole polytechnique f\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035174955","display_name":"Michele Catasta","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michele Catasta","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101446790","display_name":"Robert West","orcid":"https://orcid.org/0000-0002-3984-1232"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Robert West","raw_affiliation_strings":["\u00c9cole polytechnique f\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"\u00c9cole polytechnique f\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5035586856"],"corresponding_institution_ids":["https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":1.6798,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.86654081,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"328","last_page":"336"},"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":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.8334050178527832},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.7637187242507935},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7454137802124023},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.682522714138031},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6432124376296997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6041010618209839},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5278116464614868},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4403625726699829}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8334050178527832},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7637187242507935},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7454137802124023},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.682522714138031},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6432124376296997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6041010618209839},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5278116464614868},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4403625726699829},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3437963.3441760","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3437963.3441760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:294900","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/294900","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WoS","raw_type":"conference proceedings"},{"id":"pmh:oai:kops.uni-konstanz.de:123456789/53926","is_oa":false,"landing_page_url":"http://nbn-resolving.de/urn:nbn:de:bsz:352-2-1pl45a1ibvaju9","pdf_url":null,"source":{"id":"https://openalex.org/S4306401487","display_name":"KOPS (University of Konstanz)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I189712700","host_organization_name":"University of Konstanz","host_organization_lineage":["https://openalex.org/I189712700"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"LEWIN-EYTAN,  Liane,  Hrsg.,  David CARMEL,  Hrsg.,  Elad YOM-TOV,  Hrsg. und andere. WSDM '21 : Proceedings of the 14th ACM International Conference on Web Search and Data Mining. New York, NY: ACM, 2021, S. 328-336. ISBN 978-1-4503-8297-7. Verf\u00fcgbar unter: doi: 10.1145/3437963.3441760","raw_type":"doc-type:Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:294900","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/294900","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WoS","raw_type":"conference proceedings"},"sustainable_development_goals":[{"score":0.5,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1505422262","https://openalex.org/W1596410906","https://openalex.org/W2068737686","https://openalex.org/W2103931177","https://openalex.org/W2107598941","https://openalex.org/W2123442489","https://openalex.org/W2151209496","https://openalex.org/W2166273866","https://openalex.org/W2171150534","https://openalex.org/W2251288228","https://openalex.org/W2251612544","https://openalex.org/W2309189658","https://openalex.org/W2740083162","https://openalex.org/W2795517844","https://openalex.org/W2799188490","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2964121744","https://openalex.org/W3035487250","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W4287644835","https://openalex.org/W3092281475","https://openalex.org/W3098003361"],"abstract_inverted_index":{"We":[0],"present":[1],"Quotebank,":[2],"an":[3],"open":[4],"corpus":[5,79,100],"of":[6,45,68,77,106],"178":[7],"million":[8,20],"quotations":[9,60,107],"attributed":[10],"to":[11,31,87],"the":[12,38,43,66,75,78],"speakers":[13],"who":[14],"uttered":[15],"them,":[16],"extracted":[17],"from":[18,42,61,82],"162":[19],"English":[21],"news":[22],"articles":[23],"published":[24],"between":[25],"2008":[26],"and":[27,58,72,99,102,112],"2020.":[28],"In":[29],"order":[30],"produce":[32],"this":[33],"Web-scale":[34],"corpus,":[35],"while":[36],"at":[37,117],"same":[39],"time":[40],"benefiting":[41],"performance":[44],"modern":[46],"neural":[47],"models,":[48],"we":[49],"introduce":[50],"Quobert,":[51],"a":[52,83,93],"minimally":[53],"supervised":[54],"framework":[55],"for":[56,91],"extracting":[57],"attributing":[59],"massive":[62],"corpora.":[63],"Quobert":[64,96,113],"avoids":[65],"necessity":[67],"manually":[69],"labeled":[70],"input":[71],"instead":[73],"exploits":[74],"redundancy":[76],"by":[80],"bootstrapping":[81],"single":[84],"seed":[85],"pattern":[86],"extract":[88],"training":[89],"data":[90],"fine-tuning":[92],"BERT-based":[94],"model.":[95],"is":[97],"language-":[98],"agnostic":[101],"correctly":[103],"attributes":[104],"86.9%":[105],"in":[108],"our":[109],"experiments.":[110],"Quotebank":[111],"are":[114],"publicly":[115],"available":[116],"https://doi.org/10.5281/zenodo.4277311.":[118]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-24T08:23:43.765630","created_date":"2021-03-15T00:00:00"}