{"id":"https://openalex.org/W2914948266","doi":"https://doi.org/10.1145/3308558.3313456","title":"Place Deduplication with Embeddings","display_name":"Place Deduplication with Embeddings","publication_year":2019,"publication_date":"2019-05-13","ids":{"openalex":"https://openalex.org/W2914948266","doi":"https://doi.org/10.1145/3308558.3313456","mag":"2914948266"},"language":"en","primary_location":{"id":"doi:10.1145/3308558.3313456","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3313456","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The World Wide Web Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3308558.3313456","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006897094","display_name":"Carl Yang","orcid":"https://orcid.org/0000-0001-9145-4531"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carl Yang","raw_affiliation_strings":["University of Illinois, Urbana Champaign, 201 N Goodwin Ave, Urbana, IL 61801, USA Facebook Inc., 770 Broadway, New York, NY 10003, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana Champaign, 201 N Goodwin Ave, Urbana, IL 61801, USA Facebook Inc., 770 Broadway, New York, NY 10003, USA","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043327892","display_name":"Do Huy Hoang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Do Huy Hoang","raw_affiliation_strings":["Facebook Inc., 770 Broadway, New York, NY 10003, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Inc., 770 Broadway, New York, NY 10003, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020917394","display_name":"Tom\u00e1\u0161 Mikolov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tomas Mikolov","raw_affiliation_strings":["Facebook Inc., 770 Broadway, New York, NY 10003, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Inc., 770 Broadway, New York, NY 10003, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019539533","display_name":"Jiawei Han","orcid":"https://orcid.org/0000-0002-3629-2696"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiawei Han","raw_affiliation_strings":["University of Illinois, Urbana Champaign, 201 N Goodwin Ave, Urbana, IL 61801, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana Champaign, 201 N Goodwin Ave, Urbana, IL 61801, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3420","last_page":"3426"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11980","display_name":"Human Mobility and Location-Based Analysis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11980","display_name":"Human Mobility and Location-Based Analysis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12392","display_name":"Sharing Economy and Platforms","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/1406","display_name":"Marketing"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.984499990940094,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.798188328742981},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.6750411987304688},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5395869612693787},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4974265396595001},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.482781320810318},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.469719797372818},{"id":"https://openalex.org/keywords/graph-embedding","display_name":"Graph embedding","score":0.45989516377449036},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4530196189880371},{"id":"https://openalex.org/keywords/destinations","display_name":"Destinations","score":0.4295364022254944},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.42781105637550354},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4204443693161011},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4044863283634186},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.257279634475708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19469839334487915},{"id":"https://openalex.org/keywords/tourism","display_name":"Tourism","score":0.14849895238876343},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09422320127487183}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.798188328742981},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.6750411987304688},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5395869612693787},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4974265396595001},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.482781320810318},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.469719797372818},{"id":"https://openalex.org/C75564084","wikidata":"https://www.wikidata.org/wiki/Q5597085","display_name":"Graph embedding","level":3,"score":0.45989516377449036},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4530196189880371},{"id":"https://openalex.org/C2776687071","wikidata":"https://www.wikidata.org/wiki/Q5265193","display_name":"Destinations","level":3,"score":0.4295364022254944},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.42781105637550354},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4204443693161011},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4044863283634186},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.257279634475708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19469839334487915},{"id":"https://openalex.org/C18918823","wikidata":"https://www.wikidata.org/wiki/Q49389","display_name":"Tourism","level":2,"score":0.14849895238876343},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09422320127487183},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3308558.3313456","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3313456","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The World Wide Web Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3308558.3313456","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3313456","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The World Wide Web Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W165237679","https://openalex.org/W1516501661","https://openalex.org/W1583820951","https://openalex.org/W1950843348","https://openalex.org/W1961665379","https://openalex.org/W1971955426","https://openalex.org/W1981886741","https://openalex.org/W2017921654","https://openalex.org/W2025101014","https://openalex.org/W2037603696","https://openalex.org/W2044672016","https://openalex.org/W2047197963","https://openalex.org/W2087692915","https://openalex.org/W2095708598","https://openalex.org/W2104318727","https://openalex.org/W2109242993","https://openalex.org/W2118356770","https://openalex.org/W2124592110","https://openalex.org/W2127474081","https://openalex.org/W2140190241","https://openalex.org/W2145287260","https://openalex.org/W2153579005","https://openalex.org/W2154071538","https://openalex.org/W2167587530","https://openalex.org/W2170738476","https://openalex.org/W2187089797","https://openalex.org/W2244198747","https://openalex.org/W2265289447","https://openalex.org/W2286300105","https://openalex.org/W2338381085","https://openalex.org/W2443621726","https://openalex.org/W2467139031","https://openalex.org/W2471048925","https://openalex.org/W2493916176","https://openalex.org/W2513710618","https://openalex.org/W2536015822","https://openalex.org/W2606377603","https://openalex.org/W2608041596","https://openalex.org/W2626778328","https://openalex.org/W2648699835","https://openalex.org/W2696607001","https://openalex.org/W2741943936","https://openalex.org/W2743289629","https://openalex.org/W2767681556","https://openalex.org/W2780932362","https://openalex.org/W2809365612","https://openalex.org/W2893405056","https://openalex.org/W2898475587","https://openalex.org/W2949260486","https://openalex.org/W2949989304","https://openalex.org/W2950133940","https://openalex.org/W2951359136","https://openalex.org/W2963053846","https://openalex.org/W2963626623","https://openalex.org/W2964074409","https://openalex.org/W3099206234","https://openalex.org/W3099224353","https://openalex.org/W3102668440","https://openalex.org/W3123577293","https://openalex.org/W4294170691","https://openalex.org/W4385245566","https://openalex.org/W6630706012","https://openalex.org/W6678424907","https://openalex.org/W6685380521","https://openalex.org/W6696328460","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W3206528106","https://openalex.org/W3036264823","https://openalex.org/W2912814903","https://openalex.org/W2123605750","https://openalex.org/W2088740331","https://openalex.org/W3038102983","https://openalex.org/W2950907416","https://openalex.org/W1559483280","https://openalex.org/W2082479932","https://openalex.org/W2932872266"],"abstract_inverted_index":{"Thanks":[0],"to":[1,13,60,87,103,109],"the":[2,37,46,61,78,90,98,135],"advancing":[3],"mobile":[4],"location":[5],"services,":[6],"people":[7],"nowadays":[8],"can":[9],"post":[10],"about":[11],"places":[12,52,66],"share":[14],"visiting":[15],"experience":[16],"on-the-go.":[17],"A":[18],"large":[19],"place":[20,47,80,93,124],"graph":[21,81],"not":[22],"only":[23],"helps":[24],"users":[25],"explore":[26],"interesting":[27],"destinations,":[28],"but":[29],"also":[30],"provides":[31],"opportunities":[32],"for":[33],"understanding":[34],"and":[35,43,114],"modeling":[36],"real":[38],"world.":[39],"To":[40],"improve":[41],"coverage":[42],"flexibility":[44],"of":[45,63,92],"graph,":[48],"many":[49],"platforms":[50],"import":[51],"data":[53],"from":[54,82],"multiple":[55,127],"sources,":[56],"which":[57],"unfortunately":[58],"leads":[59],"emergence":[62],"numerous":[64],"duplicated":[65],"that":[67,107,130],"severely":[68],"hinder":[69],"subsequent":[70],"location-related":[71],"services.":[72],"In":[73],"this":[74],"work,":[75],"we":[76],"take":[77],"anonymous":[79],"Facebook":[83],"as":[84],"an":[85],"example":[86],"systematically":[88],"study":[89,100],"problem":[91],"deduplication:":[94],"We":[95],"carefully":[96],"formulate":[97],"problem,":[99],"its":[101],"connections":[102],"various":[104],"related":[105],"tasks":[106],"lead":[108],"several":[110],"promising":[111],"basic":[112],"models,":[113],"arrive":[115],"at":[116],"a":[117],"systematic":[118],"two-step":[119],"data-driven":[120],"pipeline":[121],"based":[122],"on":[123],"embedding":[125],"with":[126],"novel":[128],"techniques":[129],"works":[131],"significantly":[132],"better":[133],"than":[134],"state-of-the-art.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}