{"id":"https://openalex.org/W2584417445","doi":"https://doi.org/10.1109/bigdata.2016.7841063","title":"Large-scale taxonomy categorization for noisy product listings","display_name":"Large-scale taxonomy categorization for noisy product listings","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2584417445","doi":"https://doi.org/10.1109/bigdata.2016.7841063","mag":"2584417445"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2016.7841063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7841063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","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/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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pradipto Das","raw_affiliation_strings":["Rakuten Institute of Technology, Boston, Rakuten, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rakuten Institute of Technology, Boston, Rakuten, USA","institution_ids":["https://openalex.org/I4210144225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067274223","display_name":"Yandi Xia","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yandi Xia","raw_affiliation_strings":["Rakuten Institute of Technology, Boston, Rakuten, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rakuten Institute of Technology, Boston, Rakuten, USA","institution_ids":["https://openalex.org/I4210144225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112605862","display_name":"Aaron Levine","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aaron Levine","raw_affiliation_strings":["Rakuten Institute of Technology, Boston, Rakuten, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rakuten Institute of Technology, Boston, Rakuten, USA","institution_ids":["https://openalex.org/I4210144225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075086104","display_name":"Giuseppe Di Fabbrizio","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Giuseppe Di Fabbrizio","raw_affiliation_strings":["Rakuten Institute of Technology, Boston, Rakuten, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rakuten Institute of Technology, Boston, Rakuten, USA","institution_ids":["https://openalex.org/I4210144225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110243669","display_name":"Ankur Datta","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankur Datta","raw_affiliation_strings":["Rakuten Institute of Technology, Boston, Rakuten, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rakuten Institute of Technology, Boston, Rakuten, USA","institution_ids":["https://openalex.org/I4210144225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210144225"],"apc_list":null,"apc_paid":null,"fwci":1.7664,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.90032726,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3885","last_page":"3894"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9918000102043152,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9836999773979187,"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/categorization","display_name":"Categorization","score":0.8174206018447876},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8104165196418762},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.6636165380477905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6014136672019958},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5411857962608337},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.540166437625885},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45742782950401306},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.4411606192588806},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.4205208122730255},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41254425048828125},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3871835768222809},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3761546015739441},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09598949551582336},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08917602896690369}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8174206018447876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8104165196418762},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.6636165380477905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6014136672019958},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5411857962608337},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.540166437625885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45742782950401306},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.4411606192588806},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.4205208122730255},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41254425048828125},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3871835768222809},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3761546015739441},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09598949551582336},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08917602896690369},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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:10.1109/bigdata.2016.7841063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7841063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4399999976158142,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W172829878","https://openalex.org/W1522301498","https://openalex.org/W1532325895","https://openalex.org/W1533861849","https://openalex.org/W1538131130","https://openalex.org/W1554944419","https://openalex.org/W1678356000","https://openalex.org/W1832693441","https://openalex.org/W1880262756","https://openalex.org/W1981628148","https://openalex.org/W1984514442","https://openalex.org/W1990631563","https://openalex.org/W1991418309","https://openalex.org/W1995341420","https://openalex.org/W2091825929","https://openalex.org/W2095779006","https://openalex.org/W2099111195","https://openalex.org/W2102646738","https://openalex.org/W2118585731","https://openalex.org/W2119821739","https://openalex.org/W2122825543","https://openalex.org/W2123442489","https://openalex.org/W2124120298","https://openalex.org/W2143774383","https://openalex.org/W2148143831","https://openalex.org/W2153579005","https://openalex.org/W2163614729","https://openalex.org/W2271840356","https://openalex.org/W2295598076","https://openalex.org/W2510938745","https://openalex.org/W3102476541","https://openalex.org/W4213009331","https://openalex.org/W4239510810","https://openalex.org/W4294170691","https://openalex.org/W6607028723","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6632100814","https://openalex.org/W6639619044","https://openalex.org/W6677656871","https://openalex.org/W6682141768","https://openalex.org/W6682691769","https://openalex.org/W6683915439","https://openalex.org/W6694517276"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2125109223","https://openalex.org/W2383063829","https://openalex.org/W2138922887","https://openalex.org/W2082678934","https://openalex.org/W2035261173","https://openalex.org/W2106892947"],"abstract_inverted_index":{"E-commerce":[0],"catalogs":[1],"include":[2],"a":[3,16,26,44,74,82,109],"continuously":[4],"growing":[5],"number":[6,75],"of":[7,68,76,84],"products":[8,30],"that":[9,81],"are":[10,54],"constantly":[11],"updated.":[12],"Each":[13],"item":[14],"in":[15,43,148],"catalog":[17],"is":[18,35],"characterized":[19],"by":[20,25],"several":[21,62],"attributes":[22],"and":[23,40,79,90,107,126,142],"identified":[24],"taxonomy":[27,33,66],"label.":[28],"Categorizing":[29],"with":[31,131],"their":[32],"labels":[34],"fundamental":[36],"to":[37,52,64,103,113,138],"effectively":[38],"search":[39],"organize":[41],"listings":[42],"catalog.":[45],"However,":[46],"manual":[47,111],"and/or":[48],"rule":[49],"based":[50],"approaches":[51],"categorization":[53,67],"not":[55],"scalable.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60,98,118],"compare":[61],"classifiers":[63],"product":[65,88],"top-level":[69],"categories.":[70],"We":[71],"first":[72],"investigate":[73],"feature":[77],"sets":[78],"observe":[80],"combination":[83],"word":[85,133],"unigrams":[86],"from":[87],"names":[89],"navigational":[91],"breadcrumbs":[92],"work":[93],"best":[94],"for":[95],"categorization.":[96],"Secondly,":[97],"apply":[99],"correspondence":[100],"topic":[101],"models":[102],"detect":[104],"noisy":[105],"data":[106],"introduce":[108],"lightweight":[110],"process":[112],"improve":[114],"dataset":[115],"quality.":[116],"Finally,":[117],"evaluate":[119],"linear":[120],"models,":[121],"gradient":[122],"boosted":[123],"trees":[124],"(GBTs)":[125],"convolutional":[127],"neural":[128],"networks":[129],"(CNNs)":[130],"pre-trained":[132],"embeddings":[134],"demonstrating":[135],"that,":[136],"compared":[137],"other":[139],"baselines,":[140],"GBTs":[141],"CNNs":[143],"yield":[144],"the":[145],"highest":[146],"gains":[147],"error":[149],"reduction.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}