{"id":"https://openalex.org/W1986386500","doi":"https://doi.org/10.1145/1089815.1089817","title":"Mining knowledge from text using information extraction","display_name":"Mining knowledge from text using information extraction","publication_year":2005,"publication_date":"2005-06-01","ids":{"openalex":"https://openalex.org/W1986386500","doi":"https://doi.org/10.1145/1089815.1089817","mag":"1986386500"},"language":"en","primary_location":{"id":"doi:10.1145/1089815.1089817","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1089815.1089817","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","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/A5008715111","display_name":"Raymond J. Mooney","orcid":"https://orcid.org/0000-0002-4504-0490"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raymond J. Mooney","raw_affiliation_strings":["University of Texas at Austin, Austin, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020435927","display_name":"R\u0103zvan Bunescu","orcid":"https://orcid.org/0000-0003-2919-3566"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Razvan Bunescu","raw_affiliation_strings":["University of Texas at Austin, Austin, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":5.2263,"has_fulltext":false,"cited_by_count":296,"citation_normalized_percentile":{"value":0.96458644,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"7","issue":"1","first_page":"3","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9986000061035156,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9952999949455261,"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":0.8755873441696167},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.7517924904823303},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.7227909564971924},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5765035152435303},{"id":"https://openalex.org/keywords/biomedical-text-mining","display_name":"Biomedical text mining","score":0.5171246528625488},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5099273920059204},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.43978047370910645},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43655285239219666},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.43502259254455566},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.43320342898368835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3368704915046692}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8755873441696167},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.7517924904823303},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.7227909564971924},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5765035152435303},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.5171246528625488},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5099273920059204},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.43978047370910645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43655285239219666},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.43502259254455566},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.43320342898368835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3368704915046692},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1089815.1089817","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1089815.1089817","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.80.4183","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.80.4183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utexas.edu/users/ml/papers/text-kddexplore-05.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":84,"referenced_works":["https://openalex.org/W111352644","https://openalex.org/W116763023","https://openalex.org/W200042785","https://openalex.org/W938539187","https://openalex.org/W1484413656","https://openalex.org/W1504694836","https://openalex.org/W1506285740","https://openalex.org/W1506845741","https://openalex.org/W1520377376","https://openalex.org/W1534730506","https://openalex.org/W1553019137","https://openalex.org/W1568095077","https://openalex.org/W1592053870","https://openalex.org/W1601974683","https://openalex.org/W1623072288","https://openalex.org/W1660390307","https://openalex.org/W1670263352","https://openalex.org/W1833785989","https://openalex.org/W1896367721","https://openalex.org/W1954715867","https://openalex.org/W1982499516","https://openalex.org/W1983073929","https://openalex.org/W1986543644","https://openalex.org/W1990061958","https://openalex.org/W1991133427","https://openalex.org/W2026080185","https://openalex.org/W2038721957","https://openalex.org/W2061271742","https://openalex.org/W2066560058","https://openalex.org/W2070448217","https://openalex.org/W2071993998","https://openalex.org/W2075635421","https://openalex.org/W2075870207","https://openalex.org/W2100986601","https://openalex.org/W2102281458","https://openalex.org/W2104768328","https://openalex.org/W2104884878","https://openalex.org/W2114663556","https://openalex.org/W2115880858","https://openalex.org/W2117148965","https://openalex.org/W2117400858","https://openalex.org/W2118020653","https://openalex.org/W2120814856","https://openalex.org/W2123143128","https://openalex.org/W2124634352","https://openalex.org/W2125055259","https://openalex.org/W2125838338","https://openalex.org/W2126185232","https://openalex.org/W2127480961","https://openalex.org/W2129712609","https://openalex.org/W2135223301","https://openalex.org/W2139936633","https://openalex.org/W2143349571","https://openalex.org/W2144001613","https://openalex.org/W2144578941","https://openalex.org/W2145948275","https://openalex.org/W2147880316","https://openalex.org/W2153813903","https://openalex.org/W2156249918","https://openalex.org/W2158188757","https://openalex.org/W2158505321","https://openalex.org/W2158941357","https://openalex.org/W2161077873","https://openalex.org/W2162340487","https://openalex.org/W2164456230","https://openalex.org/W2166474856","https://openalex.org/W2167044614","https://openalex.org/W2168808732","https://openalex.org/W2201604718","https://openalex.org/W2520858206","https://openalex.org/W2560674852","https://openalex.org/W2591957553","https://openalex.org/W2595697910","https://openalex.org/W2610179052","https://openalex.org/W2613359208","https://openalex.org/W2914866334","https://openalex.org/W2962735828","https://openalex.org/W2998314454","https://openalex.org/W3007535931","https://openalex.org/W4235505822","https://openalex.org/W4255084356","https://openalex.org/W4285719527","https://openalex.org/W4290750029","https://openalex.org/W6678723247"],"related_works":["https://openalex.org/W3004288456","https://openalex.org/W2016355461","https://openalex.org/W1986386500","https://openalex.org/W1663435917","https://openalex.org/W2386938185","https://openalex.org/W2168979046","https://openalex.org/W1496929818","https://openalex.org/W2072284316","https://openalex.org/W2094989391","https://openalex.org/W2023322671"],"abstract_inverted_index":{"An":[0],"important":[1],"approach":[2],"to":[3,27,43,53,72,116],"text":[4,23,50,94],"mining":[5,92],"involves":[6],"the":[7],"use":[8],"of":[9,60,85,96],"natural-language":[10],"information":[11,113],"extraction.":[12],"Information":[13],"extraction":[14,114],"(IE)":[15],"distills":[16],"structured":[17],"data":[18,56],"or":[19,52],"knowledge":[20,47,118],"from":[21,48,57],"unstructured":[22],"by":[24],"identifying":[25],"references":[26],"named":[28],"entities":[29],"as":[30,32],"well":[31],"stated":[33],"relationships":[34],"between":[35],"such":[36],"entities.":[37],"IE":[38],"systems":[39,82],"can":[40,63],"be":[41,65],"used":[42],"directly":[44],"extricate":[45],"abstract":[46],"a":[49,58],"corpus,":[51],"extract":[54],"concrete":[55],"set":[59],"documents":[61],"which":[62],"then":[64],"further":[66],"analyzed":[67],"with":[68],"traditional":[69],"data-mining":[70],"techniques":[71],"discover":[73,117],"more":[74],"general":[75],"patterns.":[76],"We":[77,104],"discuss":[78,106],"methods":[79],"and":[80,88,101],"implemented":[81],"for":[83],"both":[84],"these":[86],"approaches":[87],"summarize":[89],"results":[90],"on":[91],"real":[93],"corpora":[95],"biomedical":[97],"abstracts,":[98],"job":[99],"announcements,":[100],"product":[102],"descriptions.":[103],"also":[105],"challenges":[107],"that":[108],"arise":[109],"when":[110],"employing":[111],"current":[112],"technology":[115],"in":[119],"text.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":35},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":20},{"year":2015,"cited_by_count":29},{"year":2014,"cited_by_count":16},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":14}],"updated_date":"2026-08-12T07:12:00.856984","created_date":"2025-10-10T00:00:00"}