{"id":"https://openalex.org/W2251827463","doi":"https://doi.org/10.3115/v1/p14-1073","title":"Robust Entity Clustering via Phylogenetic Inference","display_name":"Robust Entity Clustering via Phylogenetic Inference","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2251827463","doi":"https://doi.org/10.3115/v1/p14-1073","mag":"2251827463"},"language":"en","primary_location":{"id":"doi:10.3115/v1/p14-1073","is_oa":false,"landing_page_url":"https://doi.org/10.3115/v1/p14-1073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","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/A5111560316","display_name":"Nicholas Andrews","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nicholas Andrews","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052467896","display_name":"Jason Eisner","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Eisner","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024437840","display_name":"Mark Dredze","orcid":"https://orcid.org/0000-0002-0422-2474"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Dredze","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111560316"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":5.4971,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.95984918,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"775","last_page":"785"},"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":0.9984999895095825,"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/T11719","display_name":"Data Quality and Management","score":0.9958000183105469,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8072752356529236},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6752986907958984},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6249502897262573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6099721193313599},{"id":"https://openalex.org/keywords/coreference","display_name":"Coreference","score":0.5867080688476562},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4645763337612152},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.44778335094451904},{"id":"https://openalex.org/keywords/copying","display_name":"Copying","score":0.44745558500289917},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4238511025905609},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3980807662010193},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3756219148635864},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3333222270011902},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.1324918270111084}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8072752356529236},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6752986907958984},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6249502897262573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6099721193313599},{"id":"https://openalex.org/C28076734","wikidata":"https://www.wikidata.org/wiki/Q63087","display_name":"Coreference","level":3,"score":0.5867080688476562},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4645763337612152},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.44778335094451904},{"id":"https://openalex.org/C2779151265","wikidata":"https://www.wikidata.org/wiki/Q1156791","display_name":"Copying","level":2,"score":0.44745558500289917},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4238511025905609},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3980807662010193},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3756219148635864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3333222270011902},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.1324918270111084},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/v1/p14-1073","is_oa":false,"landing_page_url":"https://doi.org/10.3115/v1/p14-1073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.640.1333","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.640.1333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.jhu.edu/~mdredze/publications/2014_acl_phylo.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.660.8424","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.660.8424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/P/P14/P14-1073.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W509898","https://openalex.org/W46452414","https://openalex.org/W191584165","https://openalex.org/W296583332","https://openalex.org/W797920393","https://openalex.org/W1693098058","https://openalex.org/W1789782362","https://openalex.org/W1826417238","https://openalex.org/W1837702027","https://openalex.org/W1880262756","https://openalex.org/W1967573895","https://openalex.org/W1988615825","https://openalex.org/W2001082470","https://openalex.org/W2033403400","https://openalex.org/W2047834101","https://openalex.org/W2048064382","https://openalex.org/W2049633694","https://openalex.org/W2089679262","https://openalex.org/W2096335387","https://openalex.org/W2099982145","https://openalex.org/W2102443632","https://openalex.org/W2103587173","https://openalex.org/W2109215439","https://openalex.org/W2110630251","https://openalex.org/W2134737843","https://openalex.org/W2136796925","https://openalex.org/W2139694477","https://openalex.org/W2146502635","https://openalex.org/W2153848201","https://openalex.org/W2161462756","https://openalex.org/W2163131995","https://openalex.org/W2163475199","https://openalex.org/W2167146316","https://openalex.org/W2251035762","https://openalex.org/W2404643063","https://openalex.org/W2615915281"],"related_works":["https://openalex.org/W2139373276","https://openalex.org/W2227889443","https://openalex.org/W1509033667","https://openalex.org/W4385749782","https://openalex.org/W3167631113","https://openalex.org/W2145164276","https://openalex.org/W2004630825","https://openalex.org/W2324061017","https://openalex.org/W2740479527","https://openalex.org/W2765988220"],"abstract_inverted_index":{"Entity":[0],"clustering":[1],"must":[2],"determine":[3],"when":[4],"two":[5],"named-entity":[6],"mentions":[7,22,76],"refer":[8],"to":[9],"the":[10,21,75,90],"same":[11],"entity.":[12],"Typical":[13],"approaches":[14],"use":[15],"a":[16,38,71,99],"pipeline":[17],"ar-chitecture":[18],"that":[19,44,57],"clusters":[20],"using":[23],"fixed":[24],"or":[25],"learned":[26],"measures":[27],"of":[28,89],"name":[29,69],"and":[30,64,93,106],"con-text":[31],"similarity.":[32],"In":[33],"this":[34,82],"paper,":[35],"we":[36],"propose":[37],"model":[39],"for":[40,103],"cross-document":[41],"coreference":[42],"res-olution":[43],"achieves":[45],"robustness":[46],"by":[47],"learn-ing":[48],"similarity":[49],"from":[50,62,70],"unlabeled":[51],"data.":[52],"The":[53],"generative":[54],"process":[55,92],"assumes":[56],"each":[58],"entity":[59],"mention":[60],"arises":[61],"copying":[63,83],"option-ally":[65],"mutating":[66],"an":[67,107],"earlier":[68],"sim-ilar":[72],"context.":[73],"Clustering":[74],"into":[77],"entities":[78],"depends":[79],"on":[80,110],"recovering":[81],"tree":[84],"jointly":[85],"with":[86],"estimating":[87],"models":[88],"mutation":[91],"parent":[94],"selection":[95],"pro-cess.":[96],"We":[97],"present":[98],"block":[100],"Gibbs":[101],"sampler":[102],"posterior":[104],"inference":[105],"empirical":[108],"evalu-ation":[109],"several":[111],"datasets.":[112],"1":[113]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}