{"id":"https://openalex.org/W2036399631","doi":"https://doi.org/10.1007/s10032-011-0149-5","title":"Domain-specific entity extraction from noisy, unstructured data using ontology-guided search","display_name":"Domain-specific entity extraction from noisy, unstructured data using ontology-guided search","publication_year":2011,"publication_date":"2011-03-02","ids":{"openalex":"https://openalex.org/W2036399631","doi":"https://doi.org/10.1007/s10032-011-0149-5","mag":"2036399631"},"language":"en","primary_location":{"id":"doi:10.1007/s10032-011-0149-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10032-011-0149-5","pdf_url":null,"source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"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":"International Journal on Document Analysis and Recognition (IJDAR)","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/A5016172156","display_name":"Sergey Bratus","orcid":null},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sergey Bratus","raw_affiliation_strings":["Department of Computer Science, Dartmouth College, Hanover, NH, USA","Dartmouth College,,Department of Computer Science,Hanover,NH,USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Dartmouth College, Hanover, NH, USA","institution_ids":["https://openalex.org/I107672454"]},{"raw_affiliation_string":"Dartmouth College,,Department of Computer Science,Hanover,NH,USA","institution_ids":["https://openalex.org/I107672454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071360545","display_name":"Anna Rumshisky","orcid":null},"institutions":[{"id":"https://openalex.org/I6902469","display_name":"Brandeis University","ror":"https://ror.org/05abbep66","country_code":"US","type":"education","lineage":["https://openalex.org/I6902469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anna Rumshisky","raw_affiliation_strings":["Department of Computer Science, Brandeis University, Waltham, MA, USA","Brandeis University, Department of Computer Science, Waltham, MA USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Brandeis University, Waltham, MA, USA","institution_ids":["https://openalex.org/I6902469"]},{"raw_affiliation_string":"Brandeis University, Department of Computer Science, Waltham, MA USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061209890","display_name":"Alexy Khrabrov","orcid":null},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexy Khrabrov","raw_affiliation_strings":["Thayer School of Engineering, Dartmouth College, Hanover, NH, USA","Dartmouth College, Thayer School of Engineering, Hanover, NH, USA"],"affiliations":[{"raw_affiliation_string":"Thayer School of Engineering, Dartmouth College, Hanover, NH, USA","institution_ids":["https://openalex.org/I107672454"]},{"raw_affiliation_string":"Dartmouth College, Thayer School of Engineering, Hanover, NH, USA","institution_ids":["https://openalex.org/I107672454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014535450","display_name":"Rajenda Magar","orcid":null},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajenda Magar","raw_affiliation_strings":["Department of Computer Science, Dartmouth College, Hanover, NH, USA","Dartmouth College,,Department of Computer Science,Hanover,NH,USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Dartmouth College, Hanover, NH, USA","institution_ids":["https://openalex.org/I107672454"]},{"raw_affiliation_string":"Dartmouth College,,Department of Computer Science,Hanover,NH,USA","institution_ids":["https://openalex.org/I107672454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010467635","display_name":"Paul Thompson","orcid":"https://orcid.org/0000-0002-9595-3757"},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Thompson","raw_affiliation_strings":["Department of Computer Science, Dartmouth College, Hanover, NH, USA","Dartmouth College,,Department of Computer Science,Hanover,NH,USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Dartmouth College, Hanover, NH, USA","institution_ids":["https://openalex.org/I107672454"]},{"raw_affiliation_string":"Dartmouth College,,Department of Computer Science,Hanover,NH,USA","institution_ids":["https://openalex.org/I107672454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5016172156"],"corresponding_institution_ids":["https://openalex.org/I107672454"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.8194,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.76162934,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"14","issue":"2","first_page":"201","last_page":"211"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9869999885559082,"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":0.9865999817848206,"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":0.7483499646186829},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.7321759462356567},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.6411178112030029},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5565224289894104},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5513956546783447},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5014004707336426},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.47326305508613586},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4177195727825165},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38441169261932373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3536245822906494},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.10169768333435059},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0937250554561615},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.0798589289188385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483499646186829},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.7321759462356567},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.6411178112030029},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5565224289894104},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5513956546783447},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5014004707336426},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.47326305508613586},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4177195727825165},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38441169261932373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3536245822906494},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.10169768333435059},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0937250554561615},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0798589289188385},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10032-011-0149-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10032-011-0149-5","pdf_url":null,"source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"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":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W158623955","https://openalex.org/W1583837637","https://openalex.org/W1585529040","https://openalex.org/W1601867862","https://openalex.org/W1695915310","https://openalex.org/W1766290689","https://openalex.org/W1830326014","https://openalex.org/W1994929347","https://openalex.org/W1999595522","https://openalex.org/W2038721957","https://openalex.org/W2099111195","https://openalex.org/W2125838338","https://openalex.org/W2145948275","https://openalex.org/W2146071514","https://openalex.org/W2147880316","https://openalex.org/W2156515921","https://openalex.org/W2478708596","https://openalex.org/W4235505822","https://openalex.org/W4244760338","https://openalex.org/W6606580971"],"related_works":["https://openalex.org/W2030910246","https://openalex.org/W4389912246","https://openalex.org/W4205553786","https://openalex.org/W4385489363","https://openalex.org/W2372366649","https://openalex.org/W4362731990","https://openalex.org/W4316660311","https://openalex.org/W3155464240","https://openalex.org/W1516746680","https://openalex.org/W2921654184"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
