{"id":"https://openalex.org/W4385565507","doi":"https://doi.org/10.18653/v1/2023.acl-industry.18","title":"Tab-Cleaner: Weakly Supervised Tabular Data Cleaning via Pre-training for E-commerce Catalog","display_name":"Tab-Cleaner: Weakly Supervised Tabular Data Cleaning via Pre-training for E-commerce Catalog","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385565507","doi":"https://doi.org/10.18653/v1/2023.acl-industry.18"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-industry.18","pdf_url":"https://aclanthology.org/2023.acl-industry.18.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.acl-industry.18.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053337874","display_name":"Kewei Cheng","orcid":"https://orcid.org/0000-0002-2139-3451"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kewei Cheng","raw_affiliation_strings":["University of California, Los Angeles 2 Amazon,"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles 2 Amazon,","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425999","display_name":"Xian Li","orcid":"https://orcid.org/0000-0001-5714-3940"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xian Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100656202","display_name":"Zhengyang Wang","orcid":"https://orcid.org/0000-0002-5146-2884"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengyang Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011355966","display_name":"Chenwei Zhang","orcid":"https://orcid.org/0000-0002-0606-3649"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenwei Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108063115","display_name":"Binxuan Huang","orcid":"https://orcid.org/0000-0003-3571-5738"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Binxuan Huang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100626731","display_name":"Yifan Xu","orcid":"https://orcid.org/0009-0003-4239-2145"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Ethan Xu","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001402526","display_name":"Xin Luna Dong","orcid":"https://orcid.org/0009-0000-8667-322X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Luna Dong","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025213473","display_name":"Yizhou Sun","orcid":"https://orcid.org/0000-0003-1812-6843"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yizhou Sun","raw_affiliation_strings":["University of California, Los Angeles 2 Amazon,"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles 2 Amazon,","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I161318765"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":70},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Techniques and Applications","score":0.8248,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10538","display_name":"Data Mining Techniques and Applications","score":0.8248,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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 Assessment and Improvement","score":0.8236,"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/T14280","display_name":"Impact of Big Data on Society and Industry","score":0.7185,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/data-cleaning","display_name":"Data Cleaning","score":0.582608},{"id":"https://openalex.org/keywords/data-association","display_name":"Data association","score":0.47091243}],"concepts":[{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.5949772},{"id":"https://openalex.org/C2983325608","wikidata":"https://www.wikidata.org/wiki/Q17084606","display_name":"Data association","level":3,"score":0.47091243},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.47048596},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45028952},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43497875},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.33377868},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10403904},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09430796},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-industry.18","pdf_url":"https://aclanthology.org/2023.acl-industry.18.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-industry.18","pdf_url":"https://aclanthology.org/2023.acl-industry.18.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.53}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":28,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2593833795","https://openalex.org/W2608787653","https://openalex.org/W2757431232","https://openalex.org/W2889747665","https://openalex.org/W2946567085","https://openalex.org/W2962958286","https://openalex.org/W2963542836","https://openalex.org/W2963748441","https://openalex.org/W2964110616","https://openalex.org/W2964294651","https://openalex.org/W2970771982","https://openalex.org/W2971105107","https://openalex.org/W2978017171","https://openalex.org/W2986154550","https://openalex.org/W3011411500","https://openalex.org/W3015468748","https://openalex.org/W3035140194","https://openalex.org/W3035231859","https://openalex.org/W3037082750","https://openalex.org/W3098003395","https://openalex.org/W3102264439","https://openalex.org/W3158303960","https://openalex.org/W4287704453","https://openalex.org/W4287824654","https://openalex.org/W4288024261","https://openalex.org/W4312554912","https://openalex.org/W4323654151"],"related_works":["https://openalex.org/W4229560150","https://openalex.org/W4226187511","https://openalex.org/W4213217485","https://openalex.org/W4210856988","https://openalex.org/W2946721565","https://openalex.org/W2801976440","https://openalex.org/W2789518417","https://openalex.org/W2566545183","https://openalex.org/W2499449816","https://openalex.org/W2059085722"],"abstract_inverted_index":{"Kewei":[0],"Cheng,":[1],"Xian":[2],"Li,":[3],"Zhengyang":[4],"Wang,":[5],"Chenwei":[6],"Zhang,":[7],"Binxuan":[8],"Huang,":[9],"Yifan":[10],"Ethan":[11],"Xu,":[12],"Xin":[13],"Luna":[14],"Dong,":[15],"Yizhou":[16],"Sun.":[17],"Proceedings":[18],"of":[19,24],"the":[20,25],"61st":[21],"Annual":[22],"Meeting":[23],"Association":[26],"for":[27],"Computational":[28],"Linguistics":[29],"(Volume":[30],"5:":[31],"Industry":[32],"Track).":[33],"2023.":[34]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4385565507","counts_by_year":[],"updated_date":"2024-10-14T15:23:22.142111","created_date":"2023-08-05"}
