{"id":"https://openalex.org/W2540052259","doi":"https://doi.org/10.1186/s13321-016-0172-0","title":"Recognizing chemicals in patents: a comparative analysis","display_name":"Recognizing chemicals in patents: a comparative analysis","publication_year":2016,"publication_date":"2016-10-28","ids":{"openalex":"https://openalex.org/W2540052259","doi":"https://doi.org/10.1186/s13321-016-0172-0","mag":"2540052259","pmid":"https://pubmed.ncbi.nlm.nih.gov/27843493"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-016-0172-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-016-0172-0","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-016-0172-0","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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 Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-016-0172-0","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086385635","display_name":"Maryam Habibi","orcid":"https://orcid.org/0000-0002-3237-5080"},"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":"Maryam Habibi","raw_affiliation_strings":["Knowledge Management in Bioinformatics, Humboldt-Universit\u00e4t zu Berlin, 12489 Berlin, Germany","Knowledge Management in Bioinformatics, Humboldt-Universit\u00e4t zu Berlin, 12489, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Knowledge Management in Bioinformatics, Humboldt-Universit\u00e4t zu Berlin, 12489 Berlin, Germany","institution_ids":[]},{"raw_affiliation_string":"Knowledge Management in Bioinformatics, Humboldt-Universit\u00e4t zu Berlin, 12489, Berlin, Germany","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076906690","display_name":"David Luis Wiegandt","orcid":null},"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":"David Luis Wiegandt","raw_affiliation_strings":["Knowledge Management in Bioinformatics, Humboldt-Universit\u00e4t zu Berlin, 12489 Berlin, Germany","Knowledge Management in Bioinformatics, Humboldt-Universit\u00e4t zu Berlin, 12489, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Knowledge Management in Bioinformatics, Humboldt-Universit\u00e4t zu Berlin, 12489 Berlin, Germany","institution_ids":[]},{"raw_affiliation_string":"Knowledge Management in Bioinformatics, Humboldt-Universit\u00e4t zu Berlin, 12489, Berlin, Germany","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010593728","display_name":"Florian Schmedding","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139884","display_name":"Averbis (Germany)","ror":"https://ror.org/03wde7j36","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210139884"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Schmedding","raw_affiliation_strings":["Averbis GmbH, 79106 Freiburg, Germany","Averbis GmbH, 79106, Freiburg, Germany"],"affiliations":[{"raw_affiliation_string":"Averbis GmbH, 79106 Freiburg, Germany","institution_ids":["https://openalex.org/I4210139884"]},{"raw_affiliation_string":"Averbis GmbH, 79106, Freiburg, Germany","institution_ids":["https://openalex.org/I4210139884"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055236937","display_name":"Ulf Leser","orcid":"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":false,"raw_author_name":"Ulf Leser","raw_affiliation_strings":["Knowledge Management in Bioinformatics, Humboldt-Universit\u00e4t zu Berlin, 12489 Berlin, Germany","Knowledge Management in Bioinformatics, Humboldt-Universit\u00e4t zu Berlin, 12489, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Knowledge Management in Bioinformatics, Humboldt-Universit\u00e4t zu Berlin, 12489 Berlin, Germany","institution_ids":[]},{"raw_affiliation_string":"Knowledge Management in Bioinformatics, Humboldt-Universit\u00e4t zu Berlin, 12489, Berlin, Germany","institution_ids":["https://openalex.org/I39343248"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5086385635"],"corresponding_institution_ids":["https://openalex.org/I39343248"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":1.3924,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.82520944,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"8","issue":"1","first_page":"59","last_page":"59"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9980000257492065,"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":0.9980000257492065,"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/T10028","display_name":"Topic Modeling","score":0.9842000007629395,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9829000234603882,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.710054337978363},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.542426347732544},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.45434755086898804},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4299631714820862},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41104578971862793},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37573063373565674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3258489668369293},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07065850496292114}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.710054337978363},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.542426347732544},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.45434755086898804},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4299631714820862},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41104578971862793},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37573063373565674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3258489668369293},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07065850496292114},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/s13321-016-0172-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-016-0172-0","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-016-0172-0","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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 Cheminformatics","raw_type":"journal-article"},{"id":"pmid:27843493","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/27843493","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,"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 cheminformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:5086069","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5086069","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13321-016-0172-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-016-0172-0","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-016-0172-0","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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 Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321421","display_name":"Albert-Ludwigs-Universit\u00e4t Freiburg","ror":"https://ror.org/0245cg223"},{"id":"https://openalex.org/F4320323803","display_name":"Bundesministerium f\u00fcr Wirtschaft und Energie","ror":"https://ror.org/02vgg2808"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2540052259.pdf","grobid_xml":"https://content.openalex.org/works/W2540052259.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W150570035","https://openalex.org/W1539860396","https://openalex.org/W1541742946","https://openalex.org/W1601470055","https://openalex.org/W1626162317","https://openalex.org/W1986953801","https://openalex.org/W1998442020","https://openalex.org/W2026324192","https://openalex.org/W2040298461","https://openalex.org/W2044782831","https://openalex.org/W2048059249","https://openalex.org/W2054118996","https://openalex.org/W2080848531","https://openalex.org/W2095596879","https://openalex.org/W2101553882","https://openalex.org/W2107005506","https://openalex.org/W2116760667","https://openalex.org/W2132079307","https://openalex.org/W2145870108","https://openalex.org/W2149369282","https://openalex.org/W2151025545","https://openalex.org/W2165671627","https://openalex.org/W2166468803","https://openalex.org/W2168535443","https://openalex.org/W2169345623","https://openalex.org/W2169491861","https://openalex.org/W2172216479","https://openalex.org/W2250861254","https://openalex.org/W2403451154","https://openalex.org/W2406064313","https://openalex.org/W4254522893"],"related_works":["https://openalex.org/W2078793151","https://openalex.org/W3017222382","https://openalex.org/W3128216712","https://openalex.org/W3136915866","https://openalex.org/W4390279576","https://openalex.org/W2886890203","https://openalex.org/W4313535650","https://openalex.org/W2287770975","https://openalex.org/W2991463832","https://openalex.org/W3215585698"],"abstract_inverted_index":{"Recently,":[0],"methods":[1],"for":[2,16,28,54,198,205],"Chemical":[3,26],"Named":[4],"Entity":[5],"Recognition":[6],"(NER)":[7],"have":[8],"gained":[9],"substantial":[10],"interest,":[11],"driven":[12],"by":[13,50],"the":[14,35,51,59,101,113,137,141,147,179,184],"need":[15],"automatically":[17],"analyzing":[18],"todays":[19],"ever":[20],"growing":[21],"collections":[22],"of":[23,39,58,61,83,105,129,132,140],"biomedical":[24],"text.":[25],"NER":[27,43,117],"patents":[29,45,167],"is":[30,202],"particularly":[31],"essential":[32],"due":[33,99],"to":[34,94,96,100,171],"high":[36,103,207],"economic":[37],"importance":[38],"pharmaceutical":[40],"findings.":[41],"However,":[42],"on":[44,77,122,151],"has":[46],"essentially":[47],"been":[48],"neglected":[49],"research":[52],"community":[53],"long,":[55],"mostly":[56],"because":[57],"lack":[60],"enough":[62],"annotated":[63,125],"corpora.":[64],"A":[65],"recent":[66],"international":[67],"competition":[68],"specifically":[69],"targeted":[70],"this":[71],"task,":[72],"but":[73],"evaluated":[74],"tools":[75],"only":[76],"gold":[78],"standard":[79],"patent":[80,126,174],"abstracts":[81,175],"instead":[82],"full":[84,133,166,196],"patents;":[85],"furthermore,":[86],"results":[87,145],"from":[88],"such":[89],"competitions":[90],"are":[91,168],"often":[92],"difficult":[93],"extrapolate":[95],"real-life":[97],"settings":[98],"relatively":[102],"homogeneity":[104],"training":[106,199],"and":[107,120,153,156,159,176,191,200],"test":[108],"data.":[109],"Here,":[110],"we":[111],"evaluate":[112],"two":[114,128],"state-of-the-art":[115],"chemical":[116],"tools,":[118,142],"tmChem":[119],"ChemSpot,":[121],"four":[123],"different":[124],"corpora,":[127],"which":[130],"consist":[131],"texts.":[134],"We":[135],"study":[136],"overall":[138],"performance":[139],"compare":[143],"their":[144],"at":[146],"instance":[148],"level,":[149],"report":[150],"high-recall":[152],"high-precision":[154],"ensembles,":[155],"perform":[157],"cross-corpus":[158],"intra-corpus":[160],"evaluations.":[161],"Our":[162],"findings":[163],"indicate":[164],"that":[165,182],"considerably":[169],"harder":[170],"analyze":[172],"than":[173],"clearly":[177],"confirm":[178],"common":[180],"wisdom":[181],"using":[183],"same":[185],"text":[186,192,209],"genre":[187],"(patent":[188],"vs.":[189,195],"scientific)":[190],"type":[193],"(abstract":[194],"text)":[197],"testing":[201],"a":[203],"pre-requisite":[204],"achieving":[206],"quality":[208],"mining":[210],"results.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}