{"id":"https://openalex.org/W3165753548","doi":"https://doi.org/10.1145/3447548.3467434","title":"TUTA","display_name":"TUTA","publication_year":2021,"publication_date":"2021-08-13","ids":{"openalex":"https://openalex.org/W3165753548","doi":"https://doi.org/10.1145/3447548.3467434","mag":"3165753548"},"language":"en","primary_location":{"id":"doi:10.1145/3447548.3467434","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3467434","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 ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.12537","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhiruo Wang","orcid":null},"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":"Zhiruo Wang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haoyu Dong","orcid":null},"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":"Haoyu Dong","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ran Jia","orcid":null},"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":"Ran Jia","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jia Li","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Li","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiyi Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyi Fu","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shi Han","orcid":null},"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":"Shi Han","raw_affiliation_strings":["Microsoft Research, Beijing, China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":null,"display_name":"Dongmei Zhang","orcid":null},"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":"Dongmei Zhang","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":90,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1780","last_page":"1790"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9984999895095825,"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"}},{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9764000177383423,"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","display_name":"Table (database)","score":0.6083999872207642},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5073000192642212},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.36980000138282776},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.3441999852657318},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.2736000120639801}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7111999988555908},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6083999872207642},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5073000192642212},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3546000123023987},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35040000081062317},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3312999904155731},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.271699994802475},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.26510000228881836}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3447548.3467434","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3467434","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 ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.12537","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.12537","pdf_url":"https://arxiv.org/pdf/2010.12537","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.12537","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.12537","pdf_url":"https://arxiv.org/pdf/2010.12537","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2020608795","https://openalex.org/W2021167849","https://openalex.org/W2032655922","https://openalex.org/W2048282669","https://openalex.org/W2092772700","https://openalex.org/W2138556038","https://openalex.org/W2290320465","https://openalex.org/W2341748398","https://openalex.org/W2810376801","https://openalex.org/W2888184422","https://openalex.org/W2898796029","https://openalex.org/W2913178646","https://openalex.org/W2914121031","https://openalex.org/W2946504770","https://openalex.org/W2971270287","https://openalex.org/W2995580406","https://openalex.org/W2996095251","https://openalex.org/W3003937156","https://openalex.org/W3003988402","https://openalex.org/W3020935790","https://openalex.org/W3061754956","https://openalex.org/W3088604029","https://openalex.org/W3092026060","https://openalex.org/W3102264439","https://openalex.org/W3125983217","https://openalex.org/W6680679778","https://openalex.org/W6739901393"],"related_works":[],"abstract_inverted_index":{"We":[0,89],"propose":[1,58],"TUTA,":[2],"a":[3,15,34,39,93],"unified":[4,35],"pre-training":[5,77],"architecture":[6],"for":[7],"understanding":[8,14],"generally":[9,52],"structured":[10,53],"tables.":[11,54],"Noticing":[12],"that":[13,125],"table":[16,87,113,120],"requires":[17],"spatial,":[18],"hierarchical,":[19],"and":[20,48,61,69,86,99,102,119],"semantic":[21],"information,":[22],"we":[23,32,57,73],"enhance":[24],"transformers":[25],"with":[26],"three":[27,75],"novel":[28],"structure-aware":[29],"mechanisms.":[30],"First,":[31],"devise":[33,74],"tree-based":[36,59],"structure,":[37],"called":[38],"bi-dimensional":[40],"coordinate":[41],"tree,":[42],"to":[43,64,79],"describe":[44],"both":[45],"the":[46,67,83,110],"spatial":[47,68],"hierarchical":[49,70],"information":[50],"of":[51,96,112],"Upon":[55],"this,":[56],"attention":[60],"position":[62],"embedding":[63],"better":[65],"capture":[66],"information.":[71],"Moreover,":[72],"progressive":[76],"objectives":[78],"enable":[80],"representations":[81],"at":[82],"token,":[84],"cell,":[85],"levels.":[88],"pre-train":[90],"TUTA":[91,126],"on":[92,105,132],"wide":[94],"range":[95],"unlabeled":[97],"web":[98],"spreadsheet":[100],"tables":[101],"fine-tune":[103],"it":[104],"two":[106],"critical":[107],"tasks":[108],"in":[109],"field":[111],"structure":[114],"understanding:":[115],"cell":[116],"type":[117,121],"classification":[118],"classification.":[122],"Experiments":[123],"show":[124],"is":[127],"highly":[128],"effective,":[129],"achieving":[130],"state-of-the-art":[131],"five":[133],"widely-studied":[134],"datasets.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":22}],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2021-06-07T00:00:00"}