{"id":"https://openalex.org/W2103714853","doi":"https://doi.org/10.1145/1568296.1568313","title":"Using domain knowledge for ontology-guided entity extraction from noisy, unstructured text data","display_name":"Using domain knowledge for ontology-guided entity extraction from noisy, unstructured text data","publication_year":2009,"publication_date":"2009-07-23","ids":{"openalex":"https://openalex.org/W2103714853","doi":"https://doi.org/10.1145/1568296.1568313","mag":"2103714853"},"language":"en","primary_location":{"id":"doi:10.1145/1568296.1568313","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1568296.1568313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Third Workshop on Analytics for Noisy Unstructured Text 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/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":false,"raw_author_name":"Sergey Bratus","raw_affiliation_strings":["Dartmouth College, Hanover, NH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dartmouth College, Hanover, NH","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":["Brandeis University, Waltham, MA","Brandeis University , Waltham, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brandeis University, Waltham, MA","institution_ids":["https://openalex.org/I6902469"]},{"raw_affiliation_string":"Brandeis University , Waltham, MA","institution_ids":["https://openalex.org/I6902469"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030288018","display_name":"Rajendra Magar","orcid":"https://orcid.org/0000-0002-1467-6808"},"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":"Rajendra Magar","raw_affiliation_strings":["Dartmouth College, Hanover, NH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dartmouth College, Hanover, NH","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":["Dartmouth College, Hanover, NH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dartmouth College, Hanover, NH","institution_ids":["https://openalex.org/I107672454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"101","last_page":"106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9944999814033508,"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":0.9944999814033508,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9927999973297119,"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/T11719","display_name":"Data Quality and Management","score":0.9811999797821045,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.7831217050552368},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.7828230261802673},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.747275710105896},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6376638412475586},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6030210256576538},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.5920685529708862},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.5225512385368347},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.503553569316864},{"id":"https://openalex.org/keywords/health-records","display_name":"Health records","score":0.47558844089508057},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.45472991466522217},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.402651309967041},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3506091833114624},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3304026126861572},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28785932064056396},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.13836205005645752},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.13762572407722473}],"concepts":[{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.7831217050552368},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.7828230261802673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.747275710105896},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6376638412475586},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6030210256576538},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.5920685529708862},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.5225512385368347},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.503553569316864},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.47558844089508057},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.45472991466522217},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.402651309967041},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3506091833114624},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3304026126861572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28785932064056396},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.13836205005645752},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.13762572407722473},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1568296.1568313","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1568296.1568313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Third Workshop on Analytics for Noisy Unstructured Text Data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.158.2357","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.158.2357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.brandeis.edu/~arum/publications/and2009-2.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W158623955","https://openalex.org/W1601867862","https://openalex.org/W1695915310","https://openalex.org/W1766290689","https://openalex.org/W1830326014","https://openalex.org/W1999595522","https://openalex.org/W2125838338","https://openalex.org/W2145948275","https://openalex.org/W2147880316","https://openalex.org/W2156515921","https://openalex.org/W2624698084","https://openalex.org/W6638629679"],"related_works":["https://openalex.org/W2019158987","https://openalex.org/W2030910246","https://openalex.org/W2357854711","https://openalex.org/W4243448361","https://openalex.org/W4389912246","https://openalex.org/W2054759342","https://openalex.org/W4205553786","https://openalex.org/W2051700896","https://openalex.org/W1552255772","https://openalex.org/W1516746680"],"abstract_inverted_index":{"Domain-specific":[0],"knowledge":[1],"is":[2,44],"often":[3],"recorded":[4],"by":[5,89],"experts":[6],"in":[7,15,34,41],"the":[8,16,72],"form":[9],"of":[10,28,66],"unstructured":[11,58],"text.":[12],"For":[13],"example,":[14],"medical":[17],"domain,":[18],"clinical":[19],"notes":[20],"from":[21,52,62],"electronic":[22],"health":[23],"records":[24],"contain":[25],"a":[26,56,76,86],"wealth":[27],"information.":[29],"Similar":[30],"practices":[31],"are":[32],"found":[33],"other":[35],"domains.":[36],"The":[37],"challenge":[38],"we":[39],"discuss":[40],"this":[42],"paper":[43],"how":[45],"to":[46,74,82],"identify":[47],"and":[48,78],"extract":[49],"part":[50],"names":[51],"technicians":[53],"repair":[54,69,87],"notes,":[55],"noisy":[57],"text":[59],"data":[60],"source":[61],"General":[63],"Motors'":[64],"archives":[65],"solved":[67],"vehicle":[68],"problems,":[70],"with":[71],"goal":[73],"develop":[75],"robust":[77],"dynamic":[79],"reasoning":[80],"system":[81],"be":[83],"used":[84],"as":[85],"adviser":[88],"service":[90],"technicians.":[91]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"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"}
