{"id":"https://openalex.org/W2945214661","doi":"https://doi.org/10.18653/v1/p19-1400","title":"Distant Learning for Entity Linking with Automatic Noise Detection","display_name":"Distant Learning for Entity Linking with Automatic Noise Detection","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2945214661","doi":"https://doi.org/10.18653/v1/p19-1400","mag":"2945214661"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1400","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1400","pdf_url":"https://www.aclweb.org/anthology/P19-1400.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1400.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061504918","display_name":"Phong Ba Le","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Phong Le","raw_affiliation_strings":["University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086717154","display_name":"Ivan Titov","orcid":"https://orcid.org/0000-0002-2583-1893"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","NL"],"is_corresponding":true,"raw_author_name":"Ivan Titov","raw_affiliation_strings":["University of Amsterdam","University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086717154"],"corresponding_institution_ids":["https://openalex.org/I887064364","https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":3.4682,"has_fulltext":true,"cited_by_count":39,"citation_normalized_percentile":{"value":0.94136174,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4081","last_page":"4090"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987000226974487,"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":0.9986000061035156,"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":0.8178966045379639},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.69579017162323},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.6464957594871521},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6153379678726196},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6034606695175171},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5988633036613464},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.5334757566452026},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5255012512207031},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5243409276008606},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5137880444526672},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.512022078037262},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4993472099304199},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.494834840297699},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4758062958717346},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4338463246822357},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.43008002638816833},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4267916679382324},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4182227849960327},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08612766861915588},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06758776307106018}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8178966045379639},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.69579017162323},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.6464957594871521},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6153379678726196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6034606695175171},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5988633036613464},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.5334757566452026},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5255012512207031},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5243409276008606},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5137880444526672},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.512022078037262},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4993472099304199},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.494834840297699},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4758062958717346},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4338463246822357},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.43008002638816833},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4267916679382324},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4182227849960327},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08612766861915588},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06758776307106018},{"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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.18653/v1/p19-1400","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1400","pdf_url":"https://www.aclweb.org/anthology/P19-1400.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire/bb147075-13bf-4eba-b717-4a74de8c776f","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/distant-learning-for-entity-linking-with-automatic-noise-detection(bb147075-13bf-4eba-b717-4a74de8c776f).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Le, P & Titov, I 2019, Distant Learning for Entity Linking with Automatic Noise Detection. in A Korhonen, D Traum & L M\u00e0rquez (eds), The 57th Annual Meeting of the Association for Computational Linguistics : ACL 2019 : proceedings of the conference : July 28-August 2, 2019, Florence, Italy. Stroudsburg, PA, pp. 4081-4090, The 57th Annual Meeting of the Association for Computational Linguistics - ACL 2019, 28/07/19. https://doi.org/10.18653/v1/P19-1400","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:dare.uva.nl:publications/bb147075-13bf-4eba-b717-4a74de8c776f","is_oa":true,"landing_page_url":"https://hdl.handle.net/11245.1/bb147075-13bf-4eba-b717-4a74de8c776f","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Le, P & Titov, I 2019, Distant Learning for Entity Linking with Automatic Noise Detection. in A Korhonen, D Traum & L M\u00e0rquez (eds), The 57th Annual Meeting of the Association for Computational Linguistics : ACL 2019 : proceedings of the conference : July 28-August 2, 2019, Florence, Italy. Stroudsburg, PA, pp. 4081-4090, The 57th Annual Meeting of the Association for Computational Linguistics - ACL 2019, 28/07/19. https://doi.org/10.18653/v1/P19-1400","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.ed.ac.uk:publications/08ce1656-4fa7-4653-8ed8-351d67444c05","is_oa":false,"landing_page_url":"http://www.acl2019.org/EN/index.xhtml","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:publications/c0687c32-0c55-4626-8300-c44b834fb92d","is_oa":true,"landing_page_url":"https://www.aclweb.org/anthology/P19-1116","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:uvapub:oai:dare.uva.nl:publications/bb147075-13bf-4eba-b717-4a74de8c776f","is_oa":true,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/distant-learning-for-entity-linking-with-automatic-noise-detection(bb147075-13bf-4eba-b717-4a74de8c776f).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The 57th Annual Meeting of the Association for Computational Linguistics: ACL 2019 : proceedings of the conference : July 28-August 2, 2019, Florence, Italy, 4081 - 4090","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1400","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1400","pdf_url":"https://www.aclweb.org/anthology/P19-1400.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G5226226009","display_name":"Scaling Semantic Parsing to Unrestricted Domains","funder_award_id":"639.022.518","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310598","display_name":"Amazon Web Services","ror":"https://ror.org/04mv4n011"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2945214661.pdf","grobid_xml":"https://content.openalex.org/works/W2945214661.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W11298561","https://openalex.org/W1604644367","https://openalex.org/W1784290353","https://openalex.org/W2099926189","https://openalex.org/W2107598941","https://openalex.org/W2110119381","https://openalex.org/W2122052811","https://openalex.org/W2123442489","https://openalex.org/W2144578941","https://openalex.org/W2150822694","https://openalex.org/W2151048449","https://openalex.org/W2154368244","https://openalex.org/W2177768736","https://openalex.org/W2250317589","https://openalex.org/W2250539671","https://openalex.org/W2251079237","https://openalex.org/W2251894552","https://openalex.org/W2479758238","https://openalex.org/W2604314403","https://openalex.org/W2612773933","https://openalex.org/W2613223139","https://openalex.org/W2892661492","https://openalex.org/W2952087486","https://openalex.org/W2963212722","https://openalex.org/W2963691861","https://openalex.org/W3010865323"],"related_works":["https://openalex.org/W1541691357","https://openalex.org/W2090135255","https://openalex.org/W2385621242","https://openalex.org/W2168409722","https://openalex.org/W2026505290","https://openalex.org/W2782437235","https://openalex.org/W2367629516","https://openalex.org/W2086580554","https://openalex.org/W2553860513","https://openalex.org/W1993715838"],"abstract_inverted_index":{"Accurate":[0],"entity":[1,158],"linkers":[2],"have":[3],"been":[4,26],"produced":[5],"for":[6,28],"domains":[7],"and":[8,69,93,109,129,145],"languages":[9],"where":[10,31],"annotated":[11],"data":[12,39],"(i.e.,":[13],"texts":[14,74],"linked":[15],"to":[16,57,81,98,135,142],"a":[17,66,70,89,117,155],"knowledge":[18,67],"base)":[19],"is":[20,107],"available.":[21],"However,":[22],"little":[23],"progress":[24],"has":[25],"made":[27],"the":[29,76,86,104,126,150,163],"settings":[30],"no":[32],"or":[33,44],"very":[34],"limited":[35],"amounts":[36],"of":[37,72,157,165],"labeled":[38,63],"are":[40,113,133],"present":[41],"(e.g.,":[42],"legal":[43],"most":[45],"scientific":[46],"domains).":[47],"In":[48,79],"this":[49],"work,":[50],"we":[51,54,84,115],"show":[52],"how":[53],"can":[55],"learn":[56],"link":[58,146],"mentions":[59],"without":[60],"having":[61],"any":[62],"examples,":[64],"only":[65],"base":[68],"collection":[71],"unannotated":[73],"from":[75],"corresponding":[77],"domain.":[78],"order":[80],"achieve":[82],"this,":[83],"frame":[85],"task":[87],"as":[88],"multi-instance":[90],"learning":[91,105,141],"problem":[92],"rely":[94],"on":[95],"surface":[96,151],"matching":[97,152],"create":[99],"initial":[100],"noisy":[101],"labels.":[102],"As":[103],"signal":[106],"weak":[108],"our":[110,122],"surrogate":[111],"labels":[112],"noisy,":[114],"introduce":[116],"noise":[118,144],"detection":[119],"component":[120],"in":[121],"model:":[123],"it":[124,160],"lets":[125],"model":[127],"detect":[128,143],"disregard":[130],"examples":[131],"which":[132],"likely":[134],"be":[136],"noisy.":[137],"Our":[138],"method,":[139],"jointly":[140],"entities,":[147],"greatly":[148],"outperforms":[149],"baseline.":[153],"For":[154],"subset":[156],"categories,":[159],"even":[161],"approaches":[162],"performance":[164],"supervised":[166],"learning.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":6}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}