{"id":"https://openalex.org/W2101850236","doi":"https://doi.org/10.1007/s00778-014-0367-9","title":"A unified framework for approximate dictionary-based entity extraction","display_name":"A unified framework for approximate dictionary-based entity extraction","publication_year":2014,"publication_date":"2014-08-04","ids":{"openalex":"https://openalex.org/W2101850236","doi":"https://doi.org/10.1007/s00778-014-0367-9","mag":"2101850236"},"language":"en","primary_location":{"id":"doi:10.1007/s00778-014-0367-9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00778-014-0367-9","pdf_url":null,"source":{"id":"https://openalex.org/S78926909","display_name":"The VLDB Journal","issn_l":"0949-877X","issn":["0949-877X","1066-8888"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The VLDB Journal","raw_type":"journal-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/A5103237059","display_name":"Dong Deng","orcid":"https://orcid.org/0000-0002-4596-3850"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dong Deng","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China","Department of Computer Science & Technology, Tsinghua, University, Beijing, China 100084#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science & Technology, Tsinghua, University, Beijing, China 100084#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451576","display_name":"Guoliang Li","orcid":"https://orcid.org/0000-0002-1398-0621"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoliang Li","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China","Department of Computer Science & Technology, Tsinghua, University, Beijing, China 100084#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science & Technology, Tsinghua, University, Beijing, China 100084#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100951661","display_name":"Jianhua Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Feng","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China","Department of Computer Science & Technology, Tsinghua, University, Beijing, China 100084#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science & Technology, Tsinghua, University, Beijing, China 100084#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112905092","display_name":"Yi Duan","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Duan","raw_affiliation_strings":["School of Software, Beihang University, Beijing, China","School of Software, Beihang University, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Software, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Software, Beihang University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066286956","display_name":"Zhiguo Gong","orcid":"https://orcid.org/0000-0002-4588-890X"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Zhiguo Gong","raw_affiliation_strings":["University of Macau, Macau, China","Univ. of Macau, Macau, , China"],"affiliations":[{"raw_affiliation_string":"University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498"]},{"raw_affiliation_string":"Univ. of Macau, Macau, , China","institution_ids":["https://openalex.org/I204512498"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103237059"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":null,"fwci":3.3451,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.92405719,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"24","issue":"1","first_page":"143","last_page":"167"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9958000183105469,"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"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9864000082015991,"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/jaccard-index","display_name":"Jaccard index","score":0.8739382028579712},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8268479704856873},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.668635368347168},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6089842915534973},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.5742877721786499},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.5723409056663513},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5018212795257568},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.47814714908599854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43471741676330566},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36535143852233887},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32980960607528687},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.17947423458099365}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.8739382028579712},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8268479704856873},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.668635368347168},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6089842915534973},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.5742877721786499},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.5723409056663513},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5018212795257568},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.47814714908599854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43471741676330566},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36535143852233887},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32980960607528687},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.17947423458099365},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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":1,"locations":[{"id":"doi:10.1007/s00778-014-0367-9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00778-014-0367-9","pdf_url":null,"source":{"id":"https://openalex.org/S78926909","display_name":"The VLDB Journal","issn_l":"0949-877X","issn":["0949-877X","1066-8888"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The VLDB Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W125979907","https://openalex.org/W1578664299","https://openalex.org/W1973001156","https://openalex.org/W1974995373","https://openalex.org/W2055261195","https://openalex.org/W2073112656","https://openalex.org/W2073329022","https://openalex.org/W2096598900","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2098571654","https://openalex.org/W2099370490","https://openalex.org/W2100235843","https://openalex.org/W2105423800","https://openalex.org/W2105436061","https://openalex.org/W2113618143","https://openalex.org/W2115214414","https://openalex.org/W2115215982","https://openalex.org/W2119057313","https://openalex.org/W2121269638","https://openalex.org/W2121516976","https://openalex.org/W2125980212","https://openalex.org/W2127675794","https://openalex.org/W2129598390","https://openalex.org/W2131815873","https://openalex.org/W2139660688","https://openalex.org/W2147033904","https://openalex.org/W2150916025","https://openalex.org/W2159491434","https://openalex.org/W2161936973","https://openalex.org/W2166804299","https://openalex.org/W2167029568","https://openalex.org/W2167331726","https://openalex.org/W2167847032"],"related_works":["https://openalex.org/W2136519138","https://openalex.org/W1989944203","https://openalex.org/W2775696757","https://openalex.org/W4381948805","https://openalex.org/W1998479724","https://openalex.org/W4387083800","https://openalex.org/W2546839375","https://openalex.org/W4214483597","https://openalex.org/W4220978606","https://openalex.org/W4220894110"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
