{"id":"https://openalex.org/W2531117563","doi":"https://doi.org/10.1145/2872518.2889355","title":"Article De-duplication Using Distributed Representations","display_name":"Article De-duplication Using Distributed Representations","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2531117563","doi":"https://doi.org/10.1145/2872518.2889355","mag":"2531117563"},"language":"en","primary_location":{"id":"doi:10.1145/2872518.2889355","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2872518.2889355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th International Conference Companion on World Wide Web - WWW '16 Companion","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/A5081538088","display_name":"Shumpei Okura","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shumpei Okura","raw_affiliation_strings":["Yahoo Japan Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079666978","display_name":"Yukihiro Tagami","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yukihiro Tagami","raw_affiliation_strings":["Yahoo Japan Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000476077","display_name":"Akira Tajima","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Akira Tajima","raw_affiliation_strings":["Yahoo Japan Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation, Tokyo, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081538088"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4285,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79204965,"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":"87","last_page":"88"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9977999925613403,"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":0.8089853525161743},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6828383207321167},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6504331827163696},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5975929498672485},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.4961112439632416},{"id":"https://openalex.org/keywords/front-page","display_name":"Front page","score":0.4296034574508667},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3688778281211853},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.335142582654953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2644663453102112},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1268962025642395},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07640668749809265}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8089853525161743},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6828383207321167},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6504331827163696},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5975929498672485},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.4961112439632416},{"id":"https://openalex.org/C2994386881","wikidata":"https://www.wikidata.org/wiki/Q1658576","display_name":"Front page","level":2,"score":0.4296034574508667},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3688778281211853},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.335142582654953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2644663453102112},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1268962025642395},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07640668749809265},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C29595303","wikidata":"https://www.wikidata.org/wiki/Q165650","display_name":"Media studies","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2872518.2889355","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2872518.2889355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th International Conference Companion on World Wide Web - WWW '16 Companion","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2025768430","https://openalex.org/W2131744502","https://openalex.org/W2140431670"],"related_works":["https://openalex.org/W4244922520","https://openalex.org/W2062195135","https://openalex.org/W2375480909","https://openalex.org/W2353314428","https://openalex.org/W4388130299","https://openalex.org/W2012019886","https://openalex.org/W2166090428","https://openalex.org/W2381021552","https://openalex.org/W2354749003","https://openalex.org/W2377121353"],"abstract_inverted_index":{"In":[0],"news":[1],"recommendation":[2],"systems,":[3],"eliminating":[4],"redundant":[5],"information":[6,36],"is":[7,42,88],"important":[8],"as":[9,11,37],"well":[10],"providing":[12],"interesting":[13],"articles":[14,26],"for":[15,44,58,81],"users.":[16],"We":[17],"propose":[18],"a":[19],"method":[20,41,87],"that":[21],"quantifies":[22],"the":[23,34,74],"similarity":[24],"of":[25,76,98,104],"based":[27],"on":[28,90],"their":[29],"distributed":[30],"representation,":[31],"learned":[32],"with":[33],"category":[35],"weak":[38],"supervision.":[39],"This":[40],"useful":[43],"evaluation":[45,66],"under":[46],"tight":[47],"time":[48],"constraints,":[49],"since":[50],"it":[51],"only":[52],"requires":[53],"low-dimensional":[54],"inner":[55],"product":[56],"calculation":[57],"estimating":[59],"similarities.":[60,84],"The":[61],"experimental":[62],"results":[63],"from":[64],"human":[65],"and":[67,102],"online":[68],"performance":[69],"in":[70],"A/B":[71],"testing":[72],"suggest":[73],"effectiveness":[75],"our":[77],"proposed":[78],"method,":[79],"especially":[80],"quantifying":[82],"middle-level":[83],"Currently,":[85],"this":[86],"used":[89],"Yahoo!\\":[91],"JAPAN's":[92],"front":[93],"page,":[94],"which":[95],"has":[96],"millions":[97],"users":[99],"per":[100,107],"day":[101],"billions":[103],"page":[105],"views":[106],"month.":[108]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
