{"id":"https://openalex.org/W2114998795","doi":"https://doi.org/10.1145/2463676.2465284","title":"Provenance-based dictionary refinement in information extraction","display_name":"Provenance-based dictionary refinement in information extraction","publication_year":2013,"publication_date":"2013-06-22","ids":{"openalex":"https://openalex.org/W2114998795","doi":"https://doi.org/10.1145/2463676.2465284","mag":"2114998795"},"language":"en","primary_location":{"id":"doi:10.1145/2463676.2465284","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2463676.2465284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},"type":"conference-paper","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/A5110322079","display_name":"Sudeepa Roy","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sudeepa Roy","raw_affiliation_strings":["University of Washington, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050310059","display_name":"Laura Chiticariu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laura Chiticariu","raw_affiliation_strings":["IBM Research-Almaden, San Jose, CA, USA","IBM-Research Almaden, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research-Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM-Research Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054675941","display_name":"Vitaly Feldman","orcid":"https://orcid.org/0000-0002-3904-759X"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vitaly Feldman","raw_affiliation_strings":["IBM Research-Almaden, San Jose, CA, USA","IBM-Research Almaden, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research-Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM-Research Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074416632","display_name":"Frederick Reiss","orcid":"https://orcid.org/0009-0002-1254-1798"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frederick R. Reiss","raw_affiliation_strings":["IBM Research-Almaden, San Jose, CA, USA","IBM-Research Almaden, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research-Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM-Research Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076801334","display_name":"Huaiyu Zhu","orcid":"https://orcid.org/0000-0001-6918-4088"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huaiyu Zhu","raw_affiliation_strings":["IBM Research-Almaden, San Jose, CA, USA","IBM-Research Almaden, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research-Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM-Research Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1047,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.87652646,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"457","last_page":"468"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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":0.9973999857902527,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/provenance","display_name":"Provenance","score":0.748662531375885},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7386035323143005},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5527123212814331},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4645419418811798},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4386344254016876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33937013149261475},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.08453032374382019}],"concepts":[{"id":"https://openalex.org/C2780049196","wikidata":"https://www.wikidata.org/wiki/Q23582628","display_name":"Provenance","level":2,"score":0.748662531375885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7386035323143005},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5527123212814331},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4645419418811798},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4386344254016876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33937013149261475},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.08453032374382019},{"id":"https://openalex.org/C5900021","wikidata":"https://www.wikidata.org/wiki/Q163082","display_name":"Petrology","level":1,"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2463676.2465284","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2463676.2465284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.357.9644","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.357.9644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://homes.cs.washington.edu/~sudeepa/sigmod2013-dictionary.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.648.3232","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.648.3232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://researcher.watson.ibm.com/researcher/files/us-vitaly/RCFRZ_Dictionary-sigmod13.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W11298561","https://openalex.org/W70399244","https://openalex.org/W423733794","https://openalex.org/W1492228966","https://openalex.org/W1509595041","https://openalex.org/W1533057952","https://openalex.org/W1579838312","https://openalex.org/W1632114991","https://openalex.org/W1982982698","https://openalex.org/W1999563429","https://openalex.org/W2006278018","https://openalex.org/W2006912660","https://openalex.org/W2009591769","https://openalex.org/W2011039300","https://openalex.org/W2023256083","https://openalex.org/W2035266017","https://openalex.org/W2048468185","https://openalex.org/W2049633694","https://openalex.org/W2077811357","https://openalex.org/W2103931177","https://openalex.org/W2110367654","https://openalex.org/W2115010808","https://openalex.org/W2116469285","https://openalex.org/W2125399128","https://openalex.org/W2127462357","https://openalex.org/W2135767707","https://openalex.org/W2136179049","https://openalex.org/W2136856075","https://openalex.org/W2144416276","https://openalex.org/W2144578941","https://openalex.org/W2154582566","https://openalex.org/W2156454791","https://openalex.org/W2164949130","https://openalex.org/W2167541073","https://openalex.org/W2293299776","https://openalex.org/W2343954916","https://openalex.org/W2476096155","https://openalex.org/W6629655038"],"related_works":["https://openalex.org/W2354627941","https://openalex.org/W2347483153","https://openalex.org/W2353379336","https://openalex.org/W2379683085","https://openalex.org/W2363868702","https://openalex.org/W2374448931","https://openalex.org/W2376723740","https://openalex.org/W2370535391","https://openalex.org/W2370679613","https://openalex.org/W1901649692"],"abstract_inverted_index":{"Dictionaries":[0],"of":[1,49,63,66,84],"terms":[2],"and":[3,39,61,72],"phrases":[4],"(e.g.":[5],"common":[6],"person":[7],"or":[8,26],"organization":[9],"names)":[10],"are":[11,43,52],"integral":[12],"to":[13,31],"information":[14,20],"extraction":[15,41],"systems":[16],"that":[17],"extract":[18],"structured":[19],"from":[21],"unstructured":[22],"text.":[23],"Using":[24],"noisy":[25],"unrefined":[27],"dictionaries":[28],"may":[29],"lead":[30],"many":[32],"incorrect":[33,73],"results":[34,48],"even":[35],"when":[36],"highly":[37],"precise":[38],"sophisticated":[40],"rules":[42],"used.":[44],"In":[45],"general,":[46],"the":[47,50,85],"system":[51],"dependent":[53],"on":[54],"dictionary":[55],"entries":[56,67],"in":[57],"arbitrary":[58],"complex":[59],"ways,":[60],"removal":[62],"a":[64],"set":[65],"can":[68],"remove":[69],"both":[70],"correct":[71],"results.":[74,86],"Further,":[75],"any":[76],"such":[77],"refinement":[78],"critically":[79],"requires":[80],"laborious":[81],"manual":[82],"labeling":[83]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}