{"id":"https://openalex.org/W2741102098","doi":"https://doi.org/10.18653/v1/e17-1091","title":"Web-Scale Language-Independent Cataloging of Noisy Product Listings for E-Commerce","display_name":"Web-Scale Language-Independent Cataloging of Noisy Product Listings for E-Commerce","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2741102098","doi":"https://doi.org/10.18653/v1/e17-1091","mag":"2741102098"},"language":"en","primary_location":{"id":"doi:10.18653/v1/e17-1091","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/e17-1091","pdf_url":"https://www.aclweb.org/anthology/E17-1091.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Conference of the European Chapter of the\n          Association for Computational Linguistics: Volume 1, Long Papers","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/E17-1091.pdf","any_repository_has_fulltext":null},"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"]},{"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, 02110 -USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rakuten Institute of Technology, Boston, MA, 02110 -USA","institution_ids":["https://openalex.org/I63966007","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"]},{"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":"Yandi Xia","raw_affiliation_strings":["Rakuten Institute of Technology, Boston, MA, 02110 -USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rakuten Institute of Technology, Boston, MA, 02110 -USA","institution_ids":["https://openalex.org/I63966007","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"]},{"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":"Aaron Levine","raw_affiliation_strings":["Rakuten Institute of Technology, Boston, MA, 02110 -USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rakuten Institute of Technology, Boston, MA, 02110 -USA","institution_ids":["https://openalex.org/I63966007","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"]},{"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":"Giuseppe Di Fabbrizio","raw_affiliation_strings":["Rakuten Institute of Technology, Boston, MA, 02110 -USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rakuten Institute of Technology, Boston, MA, 02110 -USA","institution_ids":["https://openalex.org/I63966007","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"]},{"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":"Ankur Datta","raw_affiliation_strings":["Rakuten Institute of Technology, Boston, MA, 02110 -USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rakuten Institute of Technology, Boston, MA, 02110 -USA","institution_ids":["https://openalex.org/I63966007","https://openalex.org/I4210144225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0256,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.89978234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"969","last_page":"979"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9987000226974487,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9987000226974487,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9979000091552734,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9966999888420105,"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/computer-science","display_name":"Computer science","score":0.6938822865486145},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.52402263879776},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.48799318075180054},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.45684635639190674},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.44695717096328735},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.24807509779930115},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10794654488563538},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06706920266151428}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6938822865486145},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.52402263879776},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.48799318075180054},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.45684635639190674},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.44695717096328735},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.24807509779930115},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10794654488563538},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06706920266151428},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/e17-1091","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/e17-1091","pdf_url":"https://www.aclweb.org/anthology/E17-1091.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Conference of the European Chapter of the\n          Association for Computational Linguistics: Volume 1, Long Papers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/e17-1091","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/e17-1091","pdf_url":"https://www.aclweb.org/anthology/E17-1091.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Conference of the European Chapter of the\n          Association for Computational Linguistics: Volume 1, Long Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2741102098.pdf","grobid_xml":"https://content.openalex.org/works/W2741102098.grobid-xml"},"referenced_works_count":39,"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/W1966521601","https://openalex.org/W1981628148","https://openalex.org/W1990631563","https://openalex.org/W1991418309","https://openalex.org/W1995341420","https://openalex.org/W2012942264","https://openalex.org/W2044442377","https://openalex.org/W2051840895","https://openalex.org/W2091825929","https://openalex.org/W2095779006","https://openalex.org/W2099111195","https://openalex.org/W2102646738","https://openalex.org/W2118585731","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/W2171033594","https://openalex.org/W2271840356","https://openalex.org/W2293569829","https://openalex.org/W2295598076","https://openalex.org/W2510938745","https://openalex.org/W2579710467","https://openalex.org/W2964121744","https://openalex.org/W3102476541","https://openalex.org/W4232919069","https://openalex.org/W4239510810","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"Pradipto":[0],"Das,":[1],"Yandi":[2],"Xia,":[3],"Aaron":[4],"Levine,":[5],"Giuseppe":[6],"Di":[7],"Fabbrizio,":[8],"Ankur":[9],"Datta.":[10],"Proceedings":[11],"of":[12,16,20],"the":[13,17,21],"15th":[14],"Conference":[15],"European":[18],"Chapter":[19],"Association":[22],"for":[23],"Computational":[24],"Linguistics:":[25],"Volume":[26],"1,":[27],"Long":[28],"Papers.":[29],"2017.":[30]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}