{"id":"https://openalex.org/W106453971","doi":null,"title":"Extracting Data Records from Unstructured Biomedical Full Text","display_name":"Extracting Data Records from Unstructured Biomedical Full Text","publication_year":2007,"publication_date":"2007-06-01","ids":{"openalex":"https://openalex.org/W106453971","mag":"106453971"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.63.2544","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.63.2544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.isi.edu/natural-language/people/hovy/papers/07EMNLP-biomed-IE.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5113652594","display_name":"Donghui Feng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Donghui Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087346345","display_name":"Gully Burns","orcid":"https://orcid.org/0000-0003-1493-865X","observed_orcids":["https://orcid.org/0000-0003-1493-865X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gully Burns","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5060225743","display_name":"Eduard H. Hovy","orcid":"https://orcid.org/0000-0002-3270-7903","observed_orcids":["https://orcid.org/0000-0002-3270-7903"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eduard Hovy","raw_affiliation_strings":["[Information Sciences Institute]"],"raw_orcid":"https://orcid.org/0000-0002-3270-7903","affiliations":[{"raw_affiliation_string":"[Information Sciences Institute]","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2734,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.52356902,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"837","last_page":"846"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9848999977111816,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9848999977111816,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.006500000134110451,"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":0.0010999999940395355,"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/information-extraction","display_name":"information extraction","score":0.7519999742507935},{"id":"https://openalex.org/keywords/conditional-random-fields","display_name":"conditional random fields","score":0.8999999761581421},{"id":"https://openalex.org/keywords/unstructured-text","display_name":"unstructured text","score":0.7590000033378601}],"concepts":[{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.8293484449386597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8225691914558411},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.7832669615745544},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6551104187965393},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6339678764343262},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5417604446411133},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5280975699424744},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4902499318122864},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4688393175601959},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.46353936195373535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45643699169158936},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41157665848731995},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2628714442253113},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.1525934934616089},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07752364873886108},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.63.2544","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.63.2544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.isi.edu/natural-language/people/hovy/papers/07EMNLP-biomed-IE.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.79.2863","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.79.2863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/D/D07/D07-1088.pdf","raw_type":"text"},{"id":"mag:106453971","doi":null,"is_oa":false,"landing_page_url":"https://www.isi.edu/natural-language/people/hovy/papers/07EMNLP-biomed-IE.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Empirical Methods in Natural Language Processing","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W73274768","https://openalex.org/W1534730506","https://openalex.org/W1544923801","https://openalex.org/W1566743778","https://openalex.org/W1572970401","https://openalex.org/W1616576116","https://openalex.org/W1626945812","https://openalex.org/W1973483159","https://openalex.org/W2015551056","https://openalex.org/W2034797903","https://openalex.org/W2044520606","https://openalex.org/W2100871981","https://openalex.org/W2100873065","https://openalex.org/W2103090613","https://openalex.org/W2118612506","https://openalex.org/W2127686544","https://openalex.org/W2130581319","https://openalex.org/W2139664619","https://openalex.org/W2145687948","https://openalex.org/W2147880316","https://openalex.org/W2150721933","https://openalex.org/W2150969560","https://openalex.org/W2159083595","https://openalex.org/W2163844356","https://openalex.org/W2435251607"],"related_works":["https://openalex.org/W3085762056","https://openalex.org/W2398206147","https://openalex.org/W632931562","https://openalex.org/W7095585822","https://openalex.org/W1968750695","https://openalex.org/W3194080553","https://openalex.org/W4284694195","https://openalex.org/W2171986676","https://openalex.org/W2154219223","https://openalex.org/W2048028417"],"abstract_inverted_index":{"In":[0],"this":[1,26],"paper,":[2],"we":[3],"address":[4],"the":[5,28,72,75],"problem":[6],"of":[7,77],"extracting":[8],"data":[9,48],"records":[10],"and":[11,58,80],"their":[12],"attributes":[13],"from":[14,55,74],"unstructured":[15,56],"biomedical":[16],"full":[17],"text.":[18],"There":[19],"has":[20],"been":[21],"little":[22],"effort":[23],"reported":[24],"on":[25,84],"in":[27],"research":[29],"community.":[30],"We":[31,45,70],"argue":[32],"that":[33],"semantics":[34],"is":[35],"important":[36],"for":[37],"record":[38,49],"extraction":[39],"or":[40],"finer-grained":[41],"language":[42,53],"processing":[43],"tasks.":[44],"derive":[46],"a":[47,62],"template":[50],"including":[51],"semantic":[52],"models":[54],"text":[57],"represent":[59],"them":[60],"with":[61,88],"discourse":[63],"level":[64],"Conditional":[65],"Random":[66],"Fields":[67],"(CRF)":[68],"model.":[69],"evaluate":[71],"approach":[73],"perspective":[76],"Information":[78],"Extraction":[79],"achieve":[81],"significant":[82],"improvements":[83],"system":[85],"performance":[86],"compared":[87],"other":[89],"baseline":[90],"systems.":[91],"1":[92]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}