{"id":"https://openalex.org/W2976032707","doi":"https://doi.org/10.1145/3341981.3344237","title":"A Dataset and Baselines for e-Commerce Product Categorization","display_name":"A Dataset and Baselines for e-Commerce Product Categorization","publication_year":2019,"publication_date":"2019-09-26","ids":{"openalex":"https://openalex.org/W2976032707","doi":"https://doi.org/10.1145/3341981.3344237","mag":"2976032707"},"language":"en","primary_location":{"id":"doi:10.1145/3341981.3344237","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3341981.3344237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval","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/A5044209843","display_name":"Yiu-Chang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144225","display_name":"Rakuten (United States)","ror":"https://ror.org/04bsz5816","country_code":"US","type":"company","lineage":["https://openalex.org/I1301041018","https://openalex.org/I4210144225"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yiu-Chang Lin","raw_affiliation_strings":["Rakuten Institute of Technology, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Rakuten Institute of Technology, Boston, MA, USA","institution_ids":["https://openalex.org/I63966007","https://openalex.org/I4210144225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079007516","display_name":"Pradipto Das","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144225","display_name":"Rakuten (United States)","ror":"https://ror.org/04bsz5816","country_code":"US","type":"company","lineage":["https://openalex.org/I1301041018","https://openalex.org/I4210144225"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pradipto Das","raw_affiliation_strings":["Rakuten Institute of Technology, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Rakuten Institute of Technology, Boston, MA, USA","institution_ids":["https://openalex.org/I63966007","https://openalex.org/I4210144225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050903724","display_name":"Andrew Trotman","orcid":"https://orcid.org/0000-0003-1253-7123"},"institutions":[{"id":"https://openalex.org/I80281795","display_name":"University of Otago","ror":"https://ror.org/01jmxt844","country_code":"NZ","type":"education","lineage":["https://openalex.org/I80281795"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Andrew Trotman","raw_affiliation_strings":["University of Otago, Dunedin, New Zealand"],"affiliations":[{"raw_affiliation_string":"University of Otago, Dunedin, New Zealand","institution_ids":["https://openalex.org/I80281795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019851989","display_name":"Surya Kallumadi","orcid":null},"institutions":[{"id":"https://openalex.org/I2799939184","display_name":"Home Depot (United States)","ror":"https://ror.org/031603425","country_code":"US","type":"company","lineage":["https://openalex.org/I2799939184"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Surya Kallumadi","raw_affiliation_strings":["The Home Depot, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"The Home Depot, Atlanta, GA, USA","institution_ids":["https://openalex.org/I2799939184"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5044209843"],"corresponding_institution_ids":["https://openalex.org/I4210144225","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.5601,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75307328,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"213","last_page":"216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9807999730110168,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9807999730110168,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9793999791145325,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.975600004196167,"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/categorization","display_name":"Categorization","score":0.875379741191864},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7207995057106018},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6670423746109009},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.6318392157554626},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6314735412597656},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.5464698672294617},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.5307244062423706},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47808361053466797},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.43442171812057495},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.41706860065460205},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36728382110595703},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34784168004989624},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3293123245239258},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24929338693618774},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12034526467323303},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09181633591651917},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07878831028938293}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.875379741191864},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7207995057106018},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6670423746109009},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.6318392157554626},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6314735412597656},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.5464698672294617},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.5307244062423706},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47808361053466797},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.43442171812057495},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41706860065460205},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36728382110595703},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34784168004989624},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3293123245239258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24929338693618774},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12034526467323303},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09181633591651917},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07878831028938293},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3341981.3344237","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3341981.3344237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W127707700","https://openalex.org/W1939008705","https://openalex.org/W2095247028","https://openalex.org/W2112688502","https://openalex.org/W2125746919","https://openalex.org/W2151682009","https://openalex.org/W4243715563","https://openalex.org/W4298443330"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540","https://openalex.org/W2370459448","https://openalex.org/W2105067402"],"abstract_inverted_index":{"We":[0,73],"make":[1],"available":[2],"a":[3,7],"document":[4],"collection":[5,84],"of":[6,15,38,41,56],"million":[8],"product":[9,18,67],"titles":[10,48],"from":[11],"3,008":[12],"anonymized":[13],"categories":[14],"the":[16,31,39,42,53],"rakuten.com":[17],"catalog.":[19],"The":[20],"anonymization":[21],"has":[22],"been":[23],"done":[24],"due":[25],"to":[26],"intellectual":[27],"property":[28],"rights":[29],"on":[30,70],"underlying":[32],"data":[33],"organization":[34],"taxonomy.":[35],"Our":[36],"analysis":[37,77],"characteristics":[40],"800,000":[43],"training":[44],"and":[45,76,78,85],"20,000":[46],"validation":[47],"show":[49],"that":[50],"they":[51],"match":[52],"test":[54],"set":[55],"180,000":[57],"titles.":[58],"Twenty":[59],"six":[60],"independent":[61],"teams":[62],"participated":[63],"in":[64],"an":[65],"automatic":[66],"categorization":[68],"challenge":[69],"this":[71,83],"dataset.":[72],"present":[74],"results":[75],"suggest":[79],"strong":[80],"baselines":[81],"for":[82],"task.":[86]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
