{"id":"https://openalex.org/W1575983524","doi":"https://doi.org/10.1007/978-3-540-76298-0_8","title":"Scalable Cleanup of Information Extraction Data Using Ontologies","display_name":"Scalable Cleanup of Information Extraction Data Using Ontologies","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W1575983524","doi":"https://doi.org/10.1007/978-3-540-76298-0_8","mag":"1575983524"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-540-76298-0_8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-76298-0_8","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"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/A5012855077","display_name":"Julian Dolby","orcid":"https://orcid.org/0000-0002-6658-2678"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julian Dolby","raw_affiliation_strings":["IBM Watson Research Center,P.O. Box 704, Yorktown Heights, NY 10598, USA","[IBM Watson Research Center, Yorktown Heights, NY]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Watson Research Center,P.O. Box 704, Yorktown Heights, NY 10598, USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"[IBM Watson Research Center, Yorktown Heights, NY]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101629890","display_name":"James Fan","orcid":"https://orcid.org/0000-0001-9827-7144"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Fan","raw_affiliation_strings":["IBM Watson Research Center,P.O. Box 704, Yorktown Heights, NY 10598, USA","[IBM Watson Research Center, Yorktown Heights, NY]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Watson Research Center,P.O. Box 704, Yorktown Heights, NY 10598, USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"[IBM Watson Research Center, Yorktown Heights, NY]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062643837","display_name":"Achille Fokoue","orcid":"https://orcid.org/0000-0003-1137-1344"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Achille Fokoue","raw_affiliation_strings":["IBM Watson Research Center,P.O. Box 704, Yorktown Heights, NY 10598, USA","[IBM Watson Research Center, Yorktown Heights, NY]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Watson Research Center,P.O. Box 704, Yorktown Heights, NY 10598, USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"[IBM Watson Research Center, Yorktown Heights, NY]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111981539","display_name":"Aditya Kalyanpur","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditya Kalyanpur","raw_affiliation_strings":["IBM Watson Research Center,P.O. Box 704, Yorktown Heights, NY 10598, USA","[IBM Watson Research Center, Yorktown Heights, NY]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Watson Research Center,P.O. Box 704, Yorktown Heights, NY 10598, USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"[IBM Watson Research Center, Yorktown Heights, NY]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044239463","display_name":"Aaron Kershenbaum","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aaron Kershenbaum","raw_affiliation_strings":["IBM Watson Research Center,P.O. Box 704, Yorktown Heights, NY 10598, USA","[IBM Watson Research Center, Yorktown Heights, NY]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Watson Research Center,P.O. Box 704, Yorktown Heights, NY 10598, USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"[IBM Watson Research Center, Yorktown Heights, NY]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045799873","display_name":"Li Ma","orcid":"https://orcid.org/0000-0001-8198-5531"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Ma","raw_affiliation_strings":["IBM China Research Lab, Beijing 100094, China","IBM China Research Lab, BeiJing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Lab, Beijing 100094, China","institution_ids":["https://openalex.org/I4210126794"]},{"raw_affiliation_string":"IBM China Research Lab, BeiJing, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035086776","display_name":"William Murdock","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Murdock","raw_affiliation_strings":["IBM Watson Research Center,P.O. Box 704, Yorktown Heights, NY 10598, USA","[IBM Watson Research Center, Yorktown Heights, NY]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Watson Research Center,P.O. Box 704, Yorktown Heights, NY 10598, USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"[IBM Watson Research Center, Yorktown Heights, NY]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085594669","display_name":"Kavitha Srinivas","orcid":"https://orcid.org/0000-0003-4610-967X"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kavitha Srinivas","raw_affiliation_strings":["IBM Watson Research Center,P.O. Box 704, Yorktown Heights, NY 10598, USA","[IBM Watson Research Center, Yorktown Heights, NY]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Watson Research Center,P.O. Box 704, Yorktown Heights, NY 10598, USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"[IBM Watson Research Center, Yorktown Heights, NY]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106083788","display_name":"Christopher Welty","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Welty","raw_affiliation_strings":["IBM Watson Research Center,P.O. Box 704, Yorktown Heights, NY 10598, USA","[IBM Watson Research Center, Yorktown Heights, NY]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Watson Research Center,P.O. Box 704, Yorktown Heights, NY 10598, USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"[IBM Watson Research Center, Yorktown Heights, NY]","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"100","last_page":"113"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9994000196456909,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9994000196456909,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9947999715805054,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.9936000108718872,"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/computer-science","display_name":"Computer science","score":0.8799222707748413},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.7985574007034302},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6921854019165039},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6917040348052979},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5707883834838867},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5332462787628174},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5080709457397461},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.46884334087371826},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4668341875076294},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.28659316897392273},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2651289105415344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8799222707748413},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.7985574007034302},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6921854019165039},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6917040348052979},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5707883834838867},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5332462787628174},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5080709457397461},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.46884334087371826},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4668341875076294},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.28659316897392273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2651289105415344},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-540-76298-0_8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-76298-0_8","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.105.6735","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.105.6735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://iswc2007.semanticweb.org/papers/099.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":11,"referenced_works":["https://openalex.org/W58140099","https://openalex.org/W100862262","https://openalex.org/W154654756","https://openalex.org/W1527773682","https://openalex.org/W1601001196","https://openalex.org/W1701274269","https://openalex.org/W1859852363","https://openalex.org/W2108309071","https://openalex.org/W2120959311","https://openalex.org/W2490667291","https://openalex.org/W2912130477"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W4235240664","https://openalex.org/W2965083567","https://openalex.org/W2003333417","https://openalex.org/W4243145179","https://openalex.org/W1838576100","https://openalex.org/W2095886385","https://openalex.org/W4255875982","https://openalex.org/W4244853958","https://openalex.org/W2889616422"],"abstract_inverted_index":null,"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
