{"id":"https://openalex.org/W4297778680","doi":"https://doi.org/10.48550/arxiv.2108.06712","title":"HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation","display_name":"HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation","publication_year":2021,"publication_date":"2021-08-15","ids":{"openalex":"https://openalex.org/W4297778680","doi":"https://doi.org/10.48550/arxiv.2108.06712"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2108.06712","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.06712","pdf_url":"https://arxiv.org/pdf/2108.06712","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.06712","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058829926","display_name":"Zhoujun Cheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng, Zhoujun","raw_affiliation_strings":["Shanghai Jiao Tong University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University ,","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102019411","display_name":"Haoyu Dong","orcid":"https://orcid.org/0009-0006-9789-7564","observed_orcids":["https://orcid.org/0009-0006-9789-7564","https://orcid.org/0000-0002-5132-0341"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong, Haoyu","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059929869","display_name":"Zhiruo Wang","orcid":"https://orcid.org/0000-0002-9839-8410","observed_orcids":["https://orcid.org/0000-0002-9839-8410"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Zhiruo","raw_affiliation_strings":["Carnegie Mellon University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University ,","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100555433","display_name":"Ran Jia","orcid":"https://orcid.org/0000-0001-6153-4426","observed_orcids":["https://orcid.org/0000-0001-6153-4426"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia, Ran","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103281488","display_name":"Jiaqi Guo","orcid":"https://orcid.org/0009-0002-2464-7880","observed_orcids":["https://orcid.org/0009-0002-2464-7880","https://orcid.org/0009-0006-2187-5780"]},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo, Jiaqi","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100462446","display_name":"Yan Gao","orcid":"https://orcid.org/0000-0001-5890-9717","observed_orcids":["https://orcid.org/0000-0001-5890-9717"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao, Yan","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100306406","display_name":"Han Shi","orcid":"https://orcid.org/0009-0007-6876-5922","observed_orcids":["https://orcid.org/0009-0007-6876-5922","https://orcid.org/0009-0006-0090-5944","https://orcid.org/0009-0006-8765-6003"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han, Shi","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025118710","display_name":"Jian\u2013Guang Lou","orcid":"https://orcid.org/0000-0001-8496-033X","observed_orcids":["https://orcid.org/0000-0001-8496-033X"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lou, Jian-Guang","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100331488","display_name":"Dongmei Zhang","orcid":"https://orcid.org/0000-0002-9230-2799","observed_orcids":["https://orcid.org/0000-0002-9230-2799","https://orcid.org/0000-0002-3377-7022"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Dongmei","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":11,"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":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8384000062942505,"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":0.8384000062942505,"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":0.06949999928474426,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.029999999329447746,"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/table-question-answering","display_name":"table question answering","score":0.9309999942779541},{"id":"https://openalex.org/keywords/table-to-text-generation","display_name":"table-to-text generation","score":0.7879999876022339},{"id":"https://openalex.org/keywords/entity-alignment","display_name":"entity alignment","score":0.765999972820282},{"id":"https://openalex.org/keywords/numerical-reasoning","display_name":"numerical reasoning","score":0.8999999761581421},{"id":"https://openalex.org/keywords/statistical-reports","display_name":"statistical reports","score":0.6800000071525574},{"id":"https://openalex.org/keywords/wikipedia-tables","display_name":"Wikipedia tables","score":0.5419999957084656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8252977132797241},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6178927421569824},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.6101066470146179},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5785374641418457},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5746647119522095},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5705313682556152},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5652947425842285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5491420030593872},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5200918912887573},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4914916753768921},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43200233578681946},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.41965818405151367},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4076976776123047},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27881738543510437},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26212072372436523},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2108.06712","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.06712","pdf_url":"https://arxiv.org/pdf/2108.06712","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2108.06712","doi":"https://doi.org/10.48550/arxiv.2108.06712","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2108.06712","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2108.06712","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.06712","pdf_url":"https://arxiv.org/pdf/2108.06712","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4281656839","https://openalex.org/W7206179076","https://openalex.org/W4389518606","https://openalex.org/W2921939948","https://openalex.org/W4415108817","https://openalex.org/W2945368810","https://openalex.org/W4389524107","https://openalex.org/W4411204731","https://openalex.org/W4414414612","https://openalex.org/W4413153848"],"abstract_inverted_index":{"Tables":[0],"are":[1,84,97],"often":[2],"created":[3],"with":[4,139,148],"hierarchies,":[5],"but":[6],"existing":[7,24],"works":[8],"on":[9,14,145],"table":[10,152],"reasoning":[11,118,156,170],"mainly":[12],"focus":[13],"flat":[15],"tables":[16,22,83,147],"and":[17,36,44,52,73,76,86,93,102,109,128,136,142,154,190,213,242],"neglect":[18],"hierarchical":[19,27,58,159],"tables.":[20,59],"Hierarchical":[21],"challenge":[23,241],"methods":[25],"by":[26,107],"indexing,":[28],"as":[29,31],"well":[30],"implicit":[32],"relationships":[33],"of":[34,69,111,126,151,188,231],"calculation":[35],"semantics.":[37],"This":[38],"work":[39],"presents":[40,238],"HiTab,":[41],"a":[42,62,67,163,225,239,243],"free":[43],"open":[45],"dataset":[46,64,237],"to":[47,114,196,220],"study":[48],"question":[49],"answering":[50],"(QA)":[51],"natural":[53],"language":[54],"generation":[55,227],"(NLG)":[56],"over":[57,171],"HiTab":[60,131],"is":[61],"cross-domain":[63],"constructed":[65],"from":[66,99],"wealth":[68],"statistical":[70,120],"reports":[71],"(analyses)":[72],"Wikipedia":[74],"pages,":[75],"has":[77],"unique":[78],"characteristics:":[79],"(1)":[80],"nearly":[81],"all":[82],"hierarchical,":[85],"(2)":[87],"both":[88],"target":[89],"sentences":[90,105,138],"for":[91,95,168,246],"NLG":[92,207,218],"questions":[94],"QA":[96,134,203],"revised":[98],"original,":[100],"meaningful,":[101],"diverse":[103],"descriptive":[104,137],"authored":[106],"analysts":[108],"professions":[110],"reports.":[112],"(3)":[113],"reveal":[115],"complex":[116,178],"numerical":[117,155,179],"in":[119,201,224],"analyses,":[121],"we":[122,161,181,209],"provide":[123],"fine-grained":[124],"annotations":[125,187],"entity":[127,143,189,212],"quantity":[129,141,191,214],"alignment.":[130],"provides":[132],"10,686":[133],"pairs":[135],"well-annotated":[140],"alignment":[144,215],"3,597":[146],"broad":[149],"coverage":[150],"hierarchies":[153],"types.":[157],"Targeting":[158,177],"structure,":[160],"devise":[162],"novel":[164],"hierarchy-aware":[165],"logical":[166],"form":[167],"symbolic":[169],"tables,":[172],"which":[173,193],"shows":[174],"high":[175],"effectiveness.":[176],"reasoning,":[180],"propose":[182],"partially":[183],"supervised":[184],"training":[185],"given":[186],"alignment,":[192],"helps":[194,217],"models":[195,219],"largely":[197],"reduce":[198],"spurious":[199],"predictions":[200],"the":[202,206],"task.":[204],"In":[205],"task,":[208],"find":[210],"that":[211,235],"also":[216],"generate":[221],"better":[222],"results":[223,230],"conditional":[226],"setting.":[228],"Experiment":[229],"state-of-the-art":[232],"baselines":[233],"suggest":[234],"this":[236],"strong":[240],"valuable":[244],"benchmark":[245],"future":[247],"research.":[248]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7}],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2022-10-01T00:00:00"}