{"id":"https://openalex.org/W2741654401","doi":"https://doi.org/10.1145/3077136.3096469","title":"Structuring the Unstructured","display_name":"Structuring the Unstructured","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2741654401","doi":"https://doi.org/10.1145/3077136.3096469","mag":"2741654401"},"language":"en","primary_location":{"id":"doi:10.1145/3077136.3096469","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3077136.3096469","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5035284207","display_name":"Ido Guy","orcid":"https://orcid.org/0000-0002-5525-1064"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ido Guy","raw_affiliation_strings":["eBay Research, Netanya, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"eBay Research, Netanya, Israel","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029708595","display_name":"Kira Radinsky","orcid":"https://orcid.org/0009-0007-7918-2204"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kira Radinsky","raw_affiliation_strings":["eBay Research, Netanya, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"eBay Research, Netanya, Israel","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2158,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.466605,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1351","last_page":"1351"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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":0.9994000196456909,"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 and Management","score":0.9987000226974487,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9943000078201294,"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/structuring","display_name":"Structuring","score":0.9041292667388916},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6542644500732422},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.08130848407745361}],"concepts":[{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.9041292667388916},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6542644500732422},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.08130848407745361},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3077136.3096469","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3077136.3096469","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2008009586","https://openalex.org/W2167757616","https://openalex.org/W2336203772","https://openalex.org/W2403455801","https://openalex.org/W2517551598","https://openalex.org/W2539149364","https://openalex.org/W2604359435"],"related_works":["https://openalex.org/W2070852123","https://openalex.org/W1972789746","https://openalex.org/W2039514698","https://openalex.org/W2051088300","https://openalex.org/W4242031107","https://openalex.org/W3163861878","https://openalex.org/W1511739438","https://openalex.org/W1985075218","https://openalex.org/W1525380347","https://openalex.org/W1967445305"],"abstract_inverted_index":{"Electronic":[0],"commerce":[1],"continues":[2],"to":[3,67,70,88,103,188,200,213,240,264],"gain":[4],"popularity":[5],"in":[6,17,50,90],"recent":[7],"years.":[8],"On":[9],"eBay,":[10],"one":[11],"of":[12,21,30,85,118,146,165,173,183,193,209,235,247,262],"the":[13,18,51,92,116,138,150,153,163,171,181,191,207,225,236,245,265],"largest":[14],"on-line":[15],"marketplaces":[16],"world,":[19],"millions":[20],"new":[22],"listings":[23],"(items)":[24],"are":[25],"submitted":[26],"by":[27,41,186],"a":[28,36,42,83,119,147],"variety":[29],"sellers":[31,187],"every":[32],"day.":[33],"This":[34],"renders":[35],"rich":[37],"diverse":[38],"inventory":[39,52,80],"characterized":[40],"particularly":[43],"long":[44],"tail.":[45],"In":[46,98,109],"addition,":[47],"many":[48],"items":[49,184],"lack":[53],"basic":[54],"structured":[55],"information,":[56],"such":[57],"as":[58,130,202],"product":[59,204],"identifiers,":[60],"brand,":[61],"category,":[62],"and":[63,77,94,128,143,149,168,179,206,233,253,258],"other":[64],"properties,":[65],"due":[66],"sellers'":[68],"tendency":[69],"input":[71],"unstructured":[72,107],"information":[73,251],"only,":[74],"namely":[75],"title":[76],"description.":[78],"Such":[79],"therefore":[81,260],"requires":[82],"handful":[84],"large-scale":[86,248],"solutions":[87,237,243],"assist":[89],"organizing":[91],"data":[93,132,155,227],"gaining":[95],"business":[96],"insights.":[97],"2016,":[99],"eBay":[100,154,226],"acquired":[101],"SalesPredict":[102],"help":[104],"structure":[105],"its":[106,123,126],"data.":[108],"this":[110],"proposed":[111],"presentation,":[112],"we":[113],"will":[114,136,222],"share":[115],"story":[117],"research":[120,142],"startup":[121,148],"from":[122,141,176,218],"inception":[124],"until":[125],"acquisition":[127],"integration":[129],"eBay's":[131],"science":[133,156,228],"team.":[134],"We":[135,221],"review":[137],"numerous":[139],"challenges":[140,152,232],"engineering":[144],"perspectives":[145],"principal":[151],"organization":[157],"deals":[158],"with":[159],"today.":[160],"These":[161,242],"include":[162],"identification":[164],"duplicate,":[166],"similar,":[167],"related":[169],"products;":[170,190],"extraction":[172],"name-value":[174],"attributes":[175],"item":[177,194],"titles":[178,195],"descriptions;":[180],"matching":[182],"entered":[185],"catalog":[189],"ranking":[192],"based":[196],"on":[197],"their":[198],"likelihood":[199],"serve":[201],"\"good\"":[203],"titles;":[205],"creation":[208],"\"browse":[210],"node\"":[211],"pages":[212],"address":[214],"complex":[215],"search":[216],"queries":[217],"potential":[219],"buyers.":[220],"describe":[223],"how":[224],"team":[229],"approaches":[230],"these":[231],"some":[234],"already":[238],"launched":[239],"production.":[241],"involve":[244],"use":[246],"machine":[249],"learning,":[250],"retrieval,":[252],"natural":[254],"language":[255],"processing":[256],"techniques,":[257],"should":[259],"be":[261],"interest":[263],"SIGIR":[266],"audience":[267],"at":[268],"large.":[269]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
