{"id":"https://openalex.org/W6892778151","doi":"https://doi.org/10.5281/zenodo.11032190","title":"NewsQuote Dataset: Quote-Speaker Pairs from New Articles","display_name":"NewsQuote Dataset: Quote-Speaker Pairs from New Articles","publication_year":2024,"publication_date":"2024-04-22","ids":{"openalex":"https://openalex.org/W6892778151","doi":"https://doi.org/10.5281/zenodo.11032190"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.11032190","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.11032190","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.11032190","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhang, Wenjia","orcid":"https://orcid.org/0009-0004-5645-9926"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhang, Wenjia","raw_affiliation_strings":["University of Warwick"],"raw_orcid":"https://orcid.org/0009-0004-5645-9926","affiliations":[{"raw_affiliation_string":"University of Warwick","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gui, Lin","orcid":"https://orcid.org/0000-0002-8054-9524"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gui, Lin","raw_affiliation_strings":["King's College London"],"raw_orcid":"https://orcid.org/0000-0002-8054-9524","affiliations":[{"raw_affiliation_string":"King's College London","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Procter, Rob","orcid":"https://orcid.org/0000-0001-8059-5224"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Procter, Rob","raw_affiliation_strings":["University of Warwick"],"raw_orcid":"https://orcid.org/0000-0001-8059-5224","affiliations":[{"raw_affiliation_string":"University of Warwick","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"last","author":{"id":null,"display_name":"He, Yulan","orcid":"https://orcid.org/0000-0003-3948-5845"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"He, Yulan","raw_affiliation_strings":["King's College London"],"raw_orcid":"https://orcid.org/0000-0003-3948-5845","affiliations":[{"raw_affiliation_string":"King's College London","institution_ids":["https://openalex.org/I183935753"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5698000192642212},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.4462999999523163},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.43070000410079956},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.3718000054359436},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3402000069618225},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.3327000141143799},{"id":"https://openalex.org/keywords/publishing","display_name":"Publishing","score":0.31859999895095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5934000015258789},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5805000066757202},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5698000192642212},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4462999999523163},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.43070000410079956},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C151719136","wikidata":"https://www.wikidata.org/wiki/Q3972943","display_name":"Publishing","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2687999904155731},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C2778689934","wikidata":"https://www.wikidata.org/wiki/Q1313396","display_name":"Headline","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C2984423262","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific publishing","level":3,"score":0.2597000002861023},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2572000026702881}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.11032190","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.11032190","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.11032190","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.11032190","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7089045715","display_name":"Learning from COVID-19: An AI-enabled evidence-driven framework for claim veracity assessment during pandemics","funder_award_id":"EP/V048597/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7127835790","display_name":"A Lebesgue Integral based Approximation for Language Modelling","funder_award_id":"EP/X019063/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"To":[0,28],"seek":[1],"reliable":[2],"information":[3],"sources":[4,21],"for":[5,153,157,162],"news":[6,48,62],"events,":[7],"we":[8,31,197],"introduce":[9],"a":[10,33,45,199],"novel":[11,34],"task":[12],"of":[13,39,47,123,137,149,190,201],"expert":[14],"recommendation,":[15],"which":[16,60],"aims":[17],"to":[18],"identify":[19],"trustworthy":[20],"based":[22],"on":[23,141],"their":[24],"previously":[25],"quoted":[26],"statements.":[27],"achieve":[29],"this,":[30],"built":[32,51],"dataset,":[35,59],"called":[36],"NewsQuote,":[37],"consisting":[38],"23,571":[40,202],"quote-speaker":[41],"pairs":[42,205],"sourced":[43],"from":[44,55,72,115,209],"collection":[46],"articles.":[49],"We":[50,132],"our":[52,191],"NewsQuote":[53,193],"dataset":[54,143,237],"the":[56,80,96,103,109,116,135,142,145,166,188,217,223,229,234,248,253,260,267],"AYLIEN":[57,235],"coronavirus":[58,236],"contains":[61],"articales":[63],"published":[64],"between":[65],"November":[66],"2019":[67],"and":[68,102,112,129,147,160,179],"August":[69],"2020.":[70],"Apart":[71],"text,":[73],"each":[74,138,214],"article":[75,231],"is":[76,228],"also":[77],"accompanied":[78],"with":[79,206],"meta":[81],"data":[82,119],"such":[83],"as":[84,106,108],"authors,":[85],"keywords,":[86],"summary,":[87,196],"source,":[88],"publishing":[89],"time,":[90],"topical":[91],"categories":[92,122],"coded":[93],"by":[94,144],"both":[95],"Interactive":[97],"Advertising":[98],"Bureau":[99],"(IAB)":[100],"taxonomy":[101],"IPTC":[104],"NewsCodes,":[105],"well":[107],"recognized":[110],"entities":[111],"entity":[113],"links":[114],"DBpedia.":[117],"Our":[118],"covers":[120],"three":[121],"quotes:":[124],"direct":[125,158,181],"quote,":[126],"indirect":[127,154,173],"quote":[128],"mixed":[130,163,177],"quote.":[131],"roughly":[133],"estimated":[134],"weight":[136],"quotation":[139,150],"type":[140],"number":[146,225],"position":[148],"marks:":[151],"81%":[152],"quotes,":[155,159,174,178],"11%":[156],"7%":[161],"quotes.":[164],"In":[165,195,222],"test":[167],"set,":[168],"there":[169],"are":[170],"1,582":[171],"(79%)":[172],"178":[175],"(9%)":[176],"240":[180],"quotes":[182],"(12%).":[183],"The":[184],"following":[185],"table":[186],"shows":[187],"statistics":[189],"final":[192],"dataset.":[194],"have":[198],"total":[200],"English":[203],"speaker-quote":[204],"2,843":[207],"speakers":[208],"263":[210],"global":[211],"domains.":[212],"For":[213],"sample":[215,220],"in":[216,233,259],"dataset:":[218],"'ID':":[219],"id.":[221],"id,":[224],"before":[226,247],"'-'":[227],"corresponding":[230],"id":[232],"'Sentence':":[238],"main":[239],"sentence.":[240,249,254,261],"'Tags':":[241],"semantic":[242],"role":[243],"labels.":[244],"'Left_sentence':":[245],"context":[246,251],"'Right_sentence':":[250],"after":[252],"'Speaker':":[255],"speaker.":[256],"'Words':":[257],"words":[258],"'Verb':":[262],"trigger":[263],"verb":[264],"that":[265],"indicates":[266],"quotation.":[268,271],"'Quotation1':":[269],"possible":[270],"'Time':":[272],"publish":[273],"time.":[274],"'Entity_link':":[275],"speaker's":[276],"Dbpedia":[277],"link.":[278]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}