{"id":"https://openalex.org/W2211254319","doi":"https://doi.org/10.1109/bigdata.2015.7364059","title":"Robust and distributed web-scale near-dup document conflation in microsoft academic service","display_name":"Robust and distributed web-scale near-dup document conflation in microsoft academic service","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2211254319","doi":"https://doi.org/10.1109/bigdata.2015.7364059","mag":"2211254319"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2015.7364059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7364059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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/A5102301230","display_name":"Chieh\u2010Han Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chieh-Han Wu","raw_affiliation_strings":["Microsoft Research, Redmond One Microsoft Way Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond One Microsoft Way Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100688422","display_name":"Yang Song","orcid":"https://orcid.org/0000-0001-8252-9626"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Song","raw_affiliation_strings":["Microsoft Research, Redmond One Microsoft Way Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond One Microsoft Way Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102301230"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":2.0031,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.88011721,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2606","last_page":"2611"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994999766349792,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9990000128746033,"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/T10028","display_name":"Topic Modeling","score":0.9968000054359436,"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/conflation","display_name":"Conflation","score":0.9725385904312134},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8332319259643555},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6629951000213623},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5811322331428528},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5224418044090271},{"id":"https://openalex.org/keywords/web-service","display_name":"Web service","score":0.4849588871002197},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46058884263038635},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4344964623451233},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.42992037534713745},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.35324209928512573},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2930186986923218}],"concepts":[{"id":"https://openalex.org/C130440534","wikidata":"https://www.wikidata.org/wiki/Q14946528","display_name":"Conflation","level":2,"score":0.9725385904312134},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8332319259643555},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6629951000213623},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5811322331428528},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5224418044090271},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.4849588871002197},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46058884263038635},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4344964623451233},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.42992037534713745},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.35324209928512573},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2930186986923218},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2015.7364059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7364059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1678356000","https://openalex.org/W2012833704","https://openalex.org/W2112564748","https://openalex.org/W2145349611","https://openalex.org/W2148885851","https://openalex.org/W2562836854","https://openalex.org/W4230940751","https://openalex.org/W6682205557"],"related_works":["https://openalex.org/W2058252362","https://openalex.org/W2186092498","https://openalex.org/W1982687909","https://openalex.org/W2352149790","https://openalex.org/W2008166176","https://openalex.org/W1984630168","https://openalex.org/W2373256103","https://openalex.org/W4245621531","https://openalex.org/W1539211164","https://openalex.org/W2895592889"],"abstract_inverted_index":{"In":[0,22,50,75],"modern":[1],"web-scale":[2],"applications":[3],"that":[4,85,99],"collect":[5],"data":[6,19,37,105],"from":[7,64],"different":[8,65],"sources,":[9],"entity":[10],"conflation":[11,34],"is":[12],"a":[13,27,56,81],"challenging":[14],"task":[15],"due":[16],"to":[17,32,59,70,91],"various":[18],"quality":[20],"issues.":[21],"this":[23],"paper,":[24],"we":[25,54,79],"propose":[26,80],"robust":[28],"and":[29,107],"distributed":[30],"framework":[31,45],"perform":[33],"on":[35],"noisy":[36,104],"in":[38],"the":[39,51,71,76],"Microsoft":[40],"Academic":[41],"Service":[42],"dataset.":[43],"Our":[44],"contains":[46],"two":[47,62],"major":[48],"components.":[49],"offline":[52,89],"component,":[53,78],"train":[55],"GBDT":[57],"model":[58,90],"determine":[60],"whether":[61],"papers":[63],"sources":[66],"should":[67],"be":[68],"conflated":[69],"same":[72],"paper":[73],"entity.":[74],"online":[77],"scalable":[82],"shingling":[83],"algorithm":[84,101],"can":[86,102],"apply":[87],"our":[88,100],"over":[92],"100":[93],"million":[94],"instances.":[95],"The":[96],"result":[97],"shows":[98],"conflate":[103],"robustly":[106],"efficiently.":[108]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}