{"id":"https://openalex.org/W4318187130","doi":"https://doi.org/10.1109/bigdata55660.2022.10021012","title":"CrunchQA: A Synthetic Dataset for Question Answering over Crunchbase Knowledge Graph","display_name":"CrunchQA: A Synthetic Dataset for Question Answering over Crunchbase Knowledge Graph","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4318187130","doi":"https://doi.org/10.1109/bigdata55660.2022.10021012"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10021012","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10021012","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","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/A5100567236","display_name":"Lifan Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I258800397","display_name":"New York University Shanghai","ror":"https://ror.org/02vpsdb40","country_code":"CN","type":"education","lineage":["https://openalex.org/I258800397","https://openalex.org/I57206974"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lifan Yu","raw_affiliation_strings":["NYU Shanghai,Shanghai,China","NYU Shanghai, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NYU Shanghai,Shanghai,China","institution_ids":["https://openalex.org/I258800397"]},{"raw_affiliation_string":"NYU Shanghai, Shanghai, China","institution_ids":["https://openalex.org/I258800397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065006346","display_name":"Nadya Abdel Madjid","orcid":null},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Nadya Abdel Madjid","raw_affiliation_strings":["NYU Abu Dhabi,Abu Dhabi,UAE","NYU Abu Dhabi, Abu Dhabi, UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NYU Abu Dhabi,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I120250893"]},{"raw_affiliation_string":"NYU Abu Dhabi, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I120250893"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088762737","display_name":"Djellel Difallah","orcid":"https://orcid.org/0000-0002-7513-6047"},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Djellel Difallah","raw_affiliation_strings":["NYU Abu Dhabi,Abu Dhabi,UAE","NYU Abu Dhabi, Abu Dhabi, UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NYU Abu Dhabi,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I120250893"]},{"raw_affiliation_string":"NYU Abu Dhabi, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I120250893"]}]}],"institutions":[],"countries_distinct_count":2,"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":0.20461171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":null,"first_page":"4635","last_page":"4641"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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":0.9994999766349792,"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/T11273","display_name":"Advanced Graph Neural Networks","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/T11719","display_name":"Data Quality and Management","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8254212737083435},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6755127310752869},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.5576022863388062},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4499448835849762},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.4142827093601227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.349730521440506},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.34001123905181885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8254212737083435},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6755127310752869},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.5576022863388062},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4499448835849762},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.4142827093601227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.349730521440506},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34001123905181885}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10021012","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10021012","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1964162497","https://openalex.org/W2127795553","https://openalex.org/W2251079237","https://openalex.org/W2755637027","https://openalex.org/W2780163489","https://openalex.org/W2809769930","https://openalex.org/W2810122007","https://openalex.org/W2890961898","https://openalex.org/W2946144988","https://openalex.org/W2963448850","https://openalex.org/W2964120615","https://openalex.org/W2965723991","https://openalex.org/W2970641574","https://openalex.org/W2971155257","https://openalex.org/W2980763157","https://openalex.org/W2985603421","https://openalex.org/W2996919866","https://openalex.org/W3034862985","https://openalex.org/W3046075728","https://openalex.org/W3114211574","https://openalex.org/W3115793027","https://openalex.org/W3154075676","https://openalex.org/W3156128319","https://openalex.org/W3156983247","https://openalex.org/W3159062288","https://openalex.org/W3210975017","https://openalex.org/W4205508242","https://openalex.org/W4318823769","https://openalex.org/W6718112784","https://openalex.org/W6771655979","https://openalex.org/W6781649520"],"related_works":["https://openalex.org/W297543570","https://openalex.org/W93075631","https://openalex.org/W4292070284","https://openalex.org/W4319071221","https://openalex.org/W4313174091","https://openalex.org/W3005434123","https://openalex.org/W4231842067","https://openalex.org/W1481711077","https://openalex.org/W2076251662","https://openalex.org/W4313219769"],"abstract_inverted_index":{"The":[0,162,194],"digital":[1],"transformation":[2],"in":[3,16,81,125],"the":[4,13,49,77,104,113,166,201],"finance":[5],"and":[6,19,35,55,95,100,145,156,196],"enterprise":[7],"sector":[8],"has":[9],"been":[10],"driven":[11],"by":[12,33,88],"advances":[14],"made":[15],"big":[17],"data":[18,25,38,53],"artificial":[20],"intelligence":[21],"technologies.":[22],"For":[23],"instance,":[24],"integration":[26,50],"enables":[27],"businesses":[28],"to":[29,47,59,75,120],"make":[30],"better":[31],"decisions":[32],"consolidating":[34],"mining":[36],"heterogeneous":[37],"repositories.":[39],"In":[40],"particular,":[41],"knowledge":[42,72],"graphs":[43,73],"(KGs)":[44],"are":[45,85,198],"used":[46,183],"facilitate":[48],"of":[51],"disparate":[52],"sources":[54],"can":[56,181],"be":[57,182],"utilized":[58],"answer":[60],"complex":[61],"queries.":[62,178],"This":[63],"work":[64],"proposes":[65],"a":[66,108,117,131,185],"new":[67,109],"dataset":[68,134,188,195],"for":[69,173,189],"question-answering":[70],"on":[71,136,160,175,200],"(KGQA)":[74],"reflect":[76],"challenges":[78],"we":[79,106,129,148],"identified":[80],"real-world":[82],"applications":[83],"which":[84],"not":[86,170],"covered":[87],"existing":[89,167],"benchmarks,":[90],"namely,":[91],"multi-hop":[92,176],"constraints,":[93],"numeric":[94],"literal":[96],"embeddings,":[97],"ranking,":[98],"reification,":[99],"hyper-relations.":[101],"To":[102],"build":[103],"dataset,":[105],"create":[107,130],"Knowledge":[110],"Graph":[111],"from":[112],"Crunchbase":[114],"database":[115],"using":[116,141],"lightweight":[118],"schema":[119],"support":[121],"high-quality":[122],"entity":[123],"embeddings":[124],"large":[126],"graphs.":[127],"Next,":[128],"Question":[132],"Answering":[133],"based":[135],"natural":[137],"language":[138],"question":[139],"generation":[140],"predefined":[142],"multiple-hop":[143],"templates":[144],"paraphrasing.":[146],"Finally,":[147],"conduct":[149],"extensive":[150],"experiments":[151],"with":[152],"state-of-the-art":[153],"KGQA":[154,191],"models":[155,168],"compare":[157],"their":[158],"performance":[159],"CrunchQA.":[161],"results":[163],"show":[164],"that":[165],"do":[169],"perform":[171],"well,":[172],"example,":[174],"constrained":[177],"Hence,":[179],"CrunchQA":[180],"as":[184],"challenging":[186],"benchmark":[187],"future":[190],"reasoning":[192],"models.":[193],"scripts":[197],"available":[199],"project":[202],"repository.":[203],"<sup>1</sup>":[204]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}