{"id":"https://openalex.org/W2152035852","doi":"https://doi.org/10.1186/2041-1480-1-9","title":"Simple tricks for improving pattern-based information extraction from the biomedical literature","display_name":"Simple tricks for improving pattern-based information extraction from the biomedical literature","publication_year":2010,"publication_date":"2010-09-24","ids":{"openalex":"https://openalex.org/W2152035852","doi":"https://doi.org/10.1186/2041-1480-1-9","mag":"2152035852","pmid":"https://pubmed.ncbi.nlm.nih.gov/20868467","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/2955645"},"language":"en","primary_location":{"id":"doi:10.1186/2041-1480-1-9","doi":"https://doi.org/10.1186/2041-1480-1-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/2041-1480-1-9","pdf_url":"https://jbiomedsem.biomedcentral.com/counter/pdf/10.1186/2041-1480-1-9","source":{"id":"https://openalex.org/S172276550","display_name":"Journal of Biomedical Semantics","issn_l":"2041-1480","issn":["2041-1480"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","doyens","jufo-1","ki-jl-1","medline","norway-1","oarl","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Semantics","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jbiomedsem.biomedcentral.com/counter/pdf/10.1186/2041-1480-1-9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Quang Long Nguyen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Quang Long Nguyen","raw_affiliation_strings":["Knowledge Management in Bioinformatics, Department for Computer Science, Humboldt-Universit\u00e4t zu Berlin, Germany. leser@informatik.hu-berlin.de","Knowledge Management in Bioinformatics, Department for Computer Science, Humboldt-Universit\u00e4t zu, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Knowledge Management in Bioinformatics, Department for Computer Science, Humboldt-Universit\u00e4t zu Berlin, Germany. leser@informatik.hu-berlin.de","institution_ids":["https://openalex.org/I39343248"]},{"raw_affiliation_string":"Knowledge Management in Bioinformatics, Department for Computer Science, Humboldt-Universit\u00e4t zu, Berlin, Germany","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070226189","display_name":"Domonkos Tikk","orcid":"https://orcid.org/0009-0002-4743-1230","observed_orcids":["https://orcid.org/0009-0002-4743-1230"]},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]},{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE","HU"],"is_corresponding":false,"raw_author_name":"Domonkos Tikk","raw_affiliation_strings":["Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Hungary","Knowledge Management in Bioinformatics, Department for Computer Science, Humboldt-Universit\u00e4t zu, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Hungary","institution_ids":["https://openalex.org/I29770179"]},{"raw_affiliation_string":"Knowledge Management in Bioinformatics, Department for Computer Science, Humboldt-Universit\u00e4t zu, Berlin, Germany","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055236937","display_name":"Ulf Leser","orcid":"https://orcid.org/0000-0003-2166-9582","observed_orcids":["https://orcid.org/0000-0003-2166-9582"]},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Ulf Leser","raw_affiliation_strings":["Knowledge Management in Bioinformatics, Department for Computer Science, Humboldt-Universit\u00e4t zu, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Knowledge Management in Bioinformatics, Department for Computer Science, Humboldt-Universit\u00e4t zu, Berlin, Germany","institution_ids":["https://openalex.org/I39343248"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5055236937"],"corresponding_institution_ids":["https://openalex.org/I39343248"],"apc_list":{"value":1590,"currency":"USD","value_usd":1590},"apc_paid":{"value":1590,"currency":"USD","value_usd":1590},"fwci":0.7775,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.68954248,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"1","issue":"1","first_page":"9","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":1.0,"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":1.0,"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":0.0,"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":0.0,"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/relation-extraction","display_name":"relation extraction","score":0.953000009059906},{"id":"https://openalex.org/keywords/pattern-filtering","display_name":"pattern filtering","score":0.75},{"id":"https://openalex.org/keywords/biomedical-text-mining","display_name":"biomedical text mining","score":0.7419999837875366},{"id":"https://openalex.org/keywords/pattern-complexity","display_name":"pattern complexity","score":0.746999979019165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8914567828178406},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6787437796592712},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6545525789260864},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6530886292457581},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6251091957092285},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.6191144585609436},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5680414438247681},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.52447909116745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45793747901916504},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.4447319805622101},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39148658514022827},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37752005457878113},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3665279746055603},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/2041-1480-1-9","doi":"https://doi.org/10.1186/2041-1480-1-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/2041-1480-1-9","pdf_url":"https://jbiomedsem.biomedcentral.com/counter/pdf/10.1186/2041-1480-1-9","source":{"id":"https://openalex.org/S172276550","display_name":"Journal of Biomedical Semantics","issn_l":"2041-1480","issn":["2041-1480"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","doyens","jufo-1","ki-jl-1","medline","norway-1","oarl","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Semantics","raw_type":"journal-article"},{"id":"pmh:oai:europepmc.org:1967258","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2955645","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"},{"id":"pmid:20868467","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20868467","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of biomedical semantics","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2955645","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC2955645/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"J Biomed Semantics","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:85032091a08c4a31a0e745ae7485d745","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/85032091a08c4a31a0e745ae7485d745","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Biomedical Semantics, Vol 1, Iss 1, p 9 (2010)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/2041-1480-1-9","doi":"https://doi.org/10.1186/2041-1480-1-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/2041-1480-1-9","pdf_url":"https://jbiomedsem.biomedcentral.com/counter/pdf/10.1186/2041-1480-1-9","source":{"id":"https://openalex.org/S172276550","display_name":"Journal of Biomedical Semantics","issn_l":"2041-1480","issn":["2041-1480"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","doyens","jufo-1","ki-jl-1","medline","norway-1","oarl","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Semantics","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323346","display_name":"B\u1ed9 Gi\u00e1o d\u1ee5c v\u00e0 \u00d0\u00e0o t\u1ea1o","ror":"https://ror.org/00drv3378"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2152035852.pdf","grobid_xml":"https://content.openalex.org/works/W2152035852.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W9328536","https://openalex.org/W1480376833","https://openalex.org/W1493270114","https://openalex.org/W1759990168","https://openalex.org/W1818857488","https://openalex.org/W1915408880","https://openalex.org/W1940315767","https://openalex.org/W1975481163","https://openalex.org/W1981933378","https://openalex.org/W2032566933","https://openalex.org/W2048059249","https://openalex.org/W2054658115","https://openalex.org/W2062163602","https://openalex.org/W2064030835","https://openalex.org/W2075655036","https://openalex.org/W2097960255","https://openalex.org/W2099369363","https://openalex.org/W2103320915","https://openalex.org/W2108010925","https://openalex.org/W2108604762","https://openalex.org/W2111727122","https://openalex.org/W2120736575","https://openalex.org/W2127224553","https://openalex.org/W2142063400","https://openalex.org/W2149803936","https://openalex.org/W2151598682","https://openalex.org/W2152698860","https://openalex.org/W2156930958","https://openalex.org/W2162461580","https://openalex.org/W2163980860","https://openalex.org/W2168091548","https://openalex.org/W2168905447","https://openalex.org/W3082731548","https://openalex.org/W3197473240"],"related_works":["https://openalex.org/W2064314529","https://openalex.org/W2892045292","https://openalex.org/W2097300420","https://openalex.org/W2250591852","https://openalex.org/W1968750695","https://openalex.org/W2554865550","https://openalex.org/W2594121213","https://openalex.org/W2052547205","https://openalex.org/W134306575","https://openalex.org/W2129086686"],"abstract_inverted_index":{"BACKGROUND:":[0],"Pattern-based":[1],"approaches":[2,27],"to":[3,131,168,172,183],"relation":[4],"extraction":[5,62,125,146],"have":[6],"shown":[7],"very":[8,135],"good":[9],"results":[10],"in":[11,38,66,110],"many":[12],"areas":[13],"of":[14,23,41,52,85,91,124,143,157],"biomedical":[15],"text":[16],"mining.":[17],"However,":[18],"defining":[19],"the":[20,67,83,86,89,92,94,119,122,141,155,175],"right":[21],"set":[22],"patterns":[24,55,95,152,188],"is":[25],"difficult;":[26],"are":[28,96],"either":[29],"manual,":[30],"incurring":[31],"high":[32],"cost,":[33],"or":[34],"automatic,":[35],"often":[36],"resulting":[37],"large":[39,108],"sets":[40,51],"noisy":[42],"patterns.":[43],"RESULTS:":[44],"We":[45,73,99],"propose":[46],"several":[47],"techniques":[48,138,178],"for":[49,60,121,189],"filtering":[50,137,177],"automatically":[53,150],"generated":[54,151],"and":[56,88],"analyze":[57],"their":[58,105,173],"effectiveness":[59],"different":[61],"tasks,":[63],"as":[64,164],"defined":[65],"recent":[68],"BioNLP":[69],"2009":[70],"shared":[71],"task.":[72],"focus":[74],"on":[75,149],"simple":[76,136],"methods":[77,159,185],"that":[78,101],"only":[79],"take":[80],"into":[81],"account":[82],"complexity":[84,90],"pattern":[87],"texts":[93],"applied":[97],"to.":[98],"show":[100],"our":[102],"techniques,":[103],"despite":[104],"simplicity,":[106,174],"yield":[107],"improvements":[109],"all":[111],"tasks":[112],"we":[113],"analyzed.":[114],"For":[115],"instance,":[116],"they":[117],"raise":[118],"F-score":[120,142],"task":[123],"gene":[126],"expression":[127],"events":[128],"from":[129],"24.8%":[130],"51.9%.":[132],"CONCLUSIONS:":[133],"Already":[134],"may":[139],"improve":[140],"an":[144],"information":[145,190],"method":[147],"based":[148],"significantly.":[153],"Furthermore,":[154],"application":[156],"such":[158],"yields":[160],"a":[161],"considerable":[162],"speed-up,":[163],"fewer":[165],"matches":[166],"need":[167],"be":[169,181],"analysed.":[170],"Due":[171],"proposed":[176],"also":[179],"should":[180],"applicable":[182],"other":[184],"using":[186],"linguistic":[187],"extraction.":[191]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2016-06-24T00:00:00"}