{"id":"https://openalex.org/W2114290255","doi":"https://doi.org/10.1145/1390749.1390755","title":"Named entity normalization in user generated content","display_name":"Named entity normalization in user generated content","publication_year":2008,"publication_date":"2008-07-24","ids":{"openalex":"https://openalex.org/W2114290255","doi":"https://doi.org/10.1145/1390749.1390755","mag":"2114290255"},"language":"en","primary_location":{"id":"doi:10.1145/1390749.1390755","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390749.1390755","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Analytics for noisy unstructured text 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/A5105692190","display_name":"Valentin Jijkoun","orcid":null},"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"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Valentin Jijkoun","raw_affiliation_strings":["University of Amsterdam, Amsterdam","University of Amsterdam, (Amsterdam)"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"University of Amsterdam, (Amsterdam)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002302623","display_name":"Mahboob Alam Khalid","orcid":null},"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"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mahboob Alam Khalid","raw_affiliation_strings":["University of Amsterdam, Amsterdam","University of Amsterdam, (Amsterdam)"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"University of Amsterdam, (Amsterdam)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049970479","display_name":"M. Marx","orcid":"https://orcid.org/0000-0003-3255-3729"},"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"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Maarten Marx","raw_affiliation_strings":["University of Amsterdam, Amsterdam","University of Amsterdam, (Amsterdam)"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"University of Amsterdam, (Amsterdam)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031439294","display_name":"Maarten de Rijke","orcid":"https://orcid.org/0000-0002-1086-0202"},"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"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Maarten de Rijke","raw_affiliation_strings":["University of Amsterdam, Amsterdam","University of Amsterdam, (Amsterdam)"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"University of Amsterdam, (Amsterdam)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5105692190"],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":6.5669,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.96463148,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9973999857902527,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9969000220298767,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7767886519432068},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7089683413505554},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44650816917419434},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32715755701065063}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7767886519432068},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7089683413505554},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44650816917419434},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32715755701065063},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1390749.1390755","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390749.1390755","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Analytics for noisy unstructured text data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.146.2278","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.146.2278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.science.uva.nl/~mdr/Publications/Files/sigir2008-and-nen.pdf","raw_type":"text"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/157ca19b-56de-48e0-bdbf-2b72db4fc063","is_oa":false,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/named-entity-normalization-in-user-generated-content(157ca19b-56de-48e0-bdbf-2b72db4fc063).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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Jijkoun, V, Khalid, M A, Marx, M & de Rijke, M 2008, Named entity normalization in user generated content. in D Lopresti, S Roy, K Schulz & L V Subramaniam (eds), Proceedings of SIGIR 2008 Workshop on Analytics for Noisy Unstructured Text Data (AND 08), July 24, 2008, Singapore. ACM International Conference Proceedings Series, vol. 303, Association for Computing Machinery, New York, NY, pp. 23-30, 2nd Workshop on Analytics for Noisy Unstructured Text Data (AND 2008), Singapore, 24/07/08. https://doi.org/10.1145/1390749.1390755","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:uvapub:oai:dare.uva.nl:publications/157ca19b-56de-48e0-bdbf-2b72db4fc063","is_oa":false,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/named-entity-normalization-in-user-generated-content(157ca19b-56de-48e0-bdbf-2b72db4fc063).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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM International Conference Proceedings Series, 303, 23 - 30","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.75,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4609621432","display_name":null,"funder_award_id":"220-80-001017.001.190640.001.501640.002.501612.066.512","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G8126347896","display_name":null,"funder_award_id":"IST-033104","funder_id":"https://openalex.org/F4320334962","funder_display_name":"Sixth Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"},{"id":"https://openalex.org/F4320334962","display_name":"Sixth Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W46452414","https://openalex.org/W86887328","https://openalex.org/W1518579031","https://openalex.org/W1594274049","https://openalex.org/W1922758806","https://openalex.org/W1980892230","https://openalex.org/W2007172042","https://openalex.org/W2012350188","https://openalex.org/W2046020929","https://openalex.org/W2055840099","https://openalex.org/W2071018679","https://openalex.org/W2076031315","https://openalex.org/W2093514089","https://openalex.org/W2100986601","https://openalex.org/W2108991785","https://openalex.org/W2114188757","https://openalex.org/W2123622235","https://openalex.org/W2131357087","https://openalex.org/W2153911474","https://openalex.org/W2185787741","https://openalex.org/W2769488050","https://openalex.org/W3004104752","https://openalex.org/W3137298232"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2591697403","https://openalex.org/W2953716828","https://openalex.org/W2904857019","https://openalex.org/W2944728705","https://openalex.org/W3011538607","https://openalex.org/W2904022177","https://openalex.org/W2359348847","https://openalex.org/W4321441197","https://openalex.org/W4294432981"],"abstract_inverted_index":{"Named":[0],"entity":[1,14,23,90],"recognition":[2],"is":[3,31,94],"important":[4,32],"for":[5,76],"semantically":[6],"oriented":[7],"retrieval":[8],"tasks,":[9],"such":[10,84],"as":[11,63,85],"question":[12],"answering,":[13],"retrieval,":[15,17],"biomedical":[16],"trend":[18],"detection,":[19],"and":[20,22,66,123],"event":[21],"tracking.":[24],"In":[25],"many":[26],"of":[27,57,73,110,121],"these":[28],"tasks":[29],"it":[30,116],"to":[33,36,43,47,50],"be":[34],"able":[35],"accurately":[37],"normalize":[38],"the":[39,55,88,104,107],"recognized":[40],"entities,":[41],"i.e.,":[42],"map":[44],"surface":[45],"forms":[46,117],"unambiguous":[48],"references":[49],"real":[51],"world":[52],"entities.":[53],"Within":[54],"context":[56,109],"structured":[58],"databases,":[59],"this":[60],"task":[61,93,105],"(known":[62],"record":[64],"linkage":[65],"data":[67],"de-duplication)":[68],"has":[69,97],"been":[70],"a":[71,118],"topic":[72],"active":[74],"research":[75],"more":[77],"than":[78],"five":[79],"decades.":[80],"For":[81],"edited":[82],"content,":[83],"news":[86],"articles,":[87],"named":[89],"normalization":[91],"(NEN)":[92],"one":[95],"that":[96],"recently":[98],"attracted":[99],"considerable":[100],"attention.":[101],"We":[102],"consider":[103],"in":[106],"challenging":[108],"user":[111],"generated":[112],"content":[113],"(UGC),":[114],"where":[115],"key":[119],"ingredient":[120],"tracking":[122],"media-analysis":[124],"systems.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
