{"id":"https://openalex.org/W3080562041","doi":"https://doi.org/10.1145/3394486.3403303","title":"Automatic Validation of Textual Attribute Values in E-commerce Catalog by Learning with Limited Labeled Data","display_name":"Automatic Validation of Textual Attribute Values in E-commerce Catalog by Learning with Limited Labeled Data","publication_year":2020,"publication_date":"2020-08-20","ids":{"openalex":"https://openalex.org/W3080562041","doi":"https://doi.org/10.1145/3394486.3403303","mag":"3080562041"},"language":"en","primary_location":{"id":"doi:10.1145/3394486.3403303","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403303","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403303","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403303","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051741610","display_name":"Yaqing Wang","orcid":"https://orcid.org/0000-0003-1457-1114"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yaqing Wang","raw_affiliation_strings":["State University of New York at Buffalo, Buffalo, NY, USA"],"affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067206559","display_name":"Yifan Xu","orcid":"https://orcid.org/0000-0003-1591-0384"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Ethan Xu","raw_affiliation_strings":["Amazon.com, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066365471","display_name":"Xian Li","orcid":"https://orcid.org/0000-0003-0108-7665"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xian Li","raw_affiliation_strings":["Amazon.com, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001402526","display_name":"Xin Luna Dong","orcid":"https://orcid.org/0009-0000-8667-322X"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Luna Dong","raw_affiliation_strings":["Amazon.com, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100781385","display_name":"Jing Gao","orcid":"https://orcid.org/0000-0001-5099-6991"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Gao","raw_affiliation_strings":["State University of New York at Buffalo, Buffalo, NY, USA"],"affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051741610"],"corresponding_institution_ids":["https://openalex.org/I63190737"],"apc_list":null,"apc_paid":null,"fwci":1.5093,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.86428749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2533","last_page":"2541"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9916999936103821,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9916999936103821,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9871000051498413,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9746999740600586,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.8364819288253784},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8303819894790649},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.6836144328117371},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6424565315246582},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5642827749252319},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5486050248146057},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5375520586967468},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5177614092826843},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4376228153705597},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38151994347572327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3404087424278259},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3229495882987976},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10476440191268921},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08994236588478088}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.8364819288253784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8303819894790649},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.6836144328117371},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6424565315246582},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5642827749252319},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5486050248146057},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5375520586967468},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5177614092826843},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4376228153705597},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38151994347572327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3404087424278259},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3229495882987976},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10476440191268921},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08994236588478088},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394486.3403303","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403303","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403303","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3394486.3403303","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403303","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403303","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3829029698","display_name":null,"funder_award_id":"IIS 1747614","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8541794061","display_name":"EAGER: Medical Knowledge Graph Construction from Heterogeneous Sources","funder_award_id":"1747614","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3080562041.pdf","grobid_xml":"https://content.openalex.org/works/W3080562041.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2101234009","https://openalex.org/W2122646361","https://openalex.org/W2126398289","https://openalex.org/W2145680191","https://openalex.org/W2293363371","https://openalex.org/W2493916176","https://openalex.org/W2608787653","https://openalex.org/W2805173585","https://openalex.org/W2891365890","https://openalex.org/W2892181857","https://openalex.org/W2896457183","https://openalex.org/W2897132279","https://openalex.org/W2943865428","https://openalex.org/W2963073217","https://openalex.org/W2963077723","https://openalex.org/W2963341924","https://openalex.org/W2963403868","https://openalex.org/W2964304846","https://openalex.org/W2997591727","https://openalex.org/W3099023595"],"related_works":["https://openalex.org/W3008339103","https://openalex.org/W1667647204","https://openalex.org/W2404647514","https://openalex.org/W4247536566","https://openalex.org/W4241418540","https://openalex.org/W2018477250","https://openalex.org/W3119814709","https://openalex.org/W1508895727","https://openalex.org/W2725786787","https://openalex.org/W1590965489"],"abstract_inverted_index":{"Product":[0],"catalogs":[1],"are":[2,20,165],"valuable":[3],"resources":[4],"for":[5,103],"eCommerce":[6,131],"website.":[7,132],"In":[8,84],"the":[9,40,53,72,97,128,181,191],"catalog,":[10],"a":[11,110,114,123,157,175],"product":[12,25,68,119,129],"is":[13,48,82,122,194],"associated":[14],"with":[15],"multiple":[16],"attributes":[17],"whose":[18],"values":[19,57,102],"short":[21,124],"texts,":[22,149],"such":[23],"as":[24,109,112],"name,":[26],"brand,":[27],"functionality":[28],"and":[29,38,64],"flavor.":[30],"Usually":[31],"individual":[32],"retailers":[33],"self-report":[34],"these":[35,56],"key":[36],"values,":[37],"thus":[39],"catalog":[41],"information":[42],"unavoidably":[43],"contains":[44],"noisy":[45],"facts.":[46],"It":[47],"very":[49],"important":[50],"to":[51,60,71,89,153,167,180,186,196],"validate":[52],"correctness":[54,98],"of":[55,75,99,127,148,160,177],"in":[58,142,169,198],"order":[59],"improve":[61],"shopper":[62],"experiences":[63],"enable":[65],"more":[66],"effective":[67,78],"recommendation.":[69],"Due":[70,179],"huge":[73],"volume":[74],"products,":[76],"an":[77,91],"automatic":[79,92],"validation":[80,93,171],"approach":[81,94],"needed.":[83],"this":[85,170],"paper,":[86],"we":[87],"propose":[88],"develop":[90],"that":[95],"verifies":[96],"textual":[100,115,125],"attribute":[101,116],"products.":[104],"This":[105],"can":[106],"be":[107,154,187],"formulated":[108],"task":[111],"cross-checking":[113,144],"value":[117],"against":[118],"profile,":[120],"which":[121,164,193],"description":[126],"on":[130,189],"Although":[133],"existing":[134],"deep":[135],"neural":[136],"network":[137],"models":[138],"have":[139],"shown":[140],"success":[141,151],"conducting":[143],"between":[145],"two":[146],"pieces":[147],"their":[150],"has":[152,185],"dependent":[155],"upon":[156],"large":[158],"set":[159],"quality":[161],"labeled":[162],"data,":[163],"hard":[166],"obtain":[168],"task:":[172],"products":[173],"span":[174],"variety":[176],"categories.":[178],"category":[182],"difference,":[183],"annotation":[184],"done":[188],"all":[190],"categories,":[192],"impossible":[195],"achieve":[197],"real":[199],"practice.":[200]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}