{"id":"https://openalex.org/W4297461106","doi":"https://doi.org/10.1093/database/baac074","title":"Full-text chemical identification with improved generalizability and tagging consistency","display_name":"Full-text chemical identification with improved generalizability and tagging consistency","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4297461106","doi":"https://doi.org/10.1093/database/baac074","pmid":"https://pubmed.ncbi.nlm.nih.gov/36170114"},"language":"en","primary_location":{"id":"doi:10.1093/database/baac074","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baac074","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baac074/46128942/baac074.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baac074/46128942/baac074.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083644268","display_name":"Hyunjae Kim","orcid":"https://orcid.org/0000-0003-2996-2564"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunjae Kim","raw_affiliation_strings":["Department of Computer Science and Engineering, Korea University , Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-2996-2564","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Korea University , Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020746366","display_name":"Mujeen Sung","orcid":"https://orcid.org/0000-0002-7978-8114"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mujeen Sung","raw_affiliation_strings":["Department of Computer Science and Engineering, Korea University , Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-7978-8114","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Korea University , Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012809586","display_name":"Wonjin Yoon","orcid":"https://orcid.org/0000-0002-6435-548X"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonjin Yoon","raw_affiliation_strings":["Department of Computer Science and Engineering, Korea University , Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-6435-548X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Korea University , Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100679181","display_name":"Sungjoon Park","orcid":"https://orcid.org/0000-0002-1132-9085"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sungjoon Park","raw_affiliation_strings":["Department of Medicine, University of California , San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medicine, University of California , San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076917278","display_name":"Jaewoo Kang","orcid":"https://orcid.org/0000-0001-6798-9106"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jaewoo Kang","raw_affiliation_strings":["AIGEN Sciences, Seoul , South Korea","Department of Computer Science and Engineering, Korea University , Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-6798-9106","affiliations":[{"raw_affiliation_string":"AIGEN Sciences, Seoul , South Korea","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Korea University , Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5076917278"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":{"value":1415,"currency":"GBP","value_usd":1735},"apc_paid":{"value":1415,"currency":"GBP","value_usd":1735},"fwci":0.1161,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53126219,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"2022","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9993000030517578,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996999979019165,"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":0.8253366351127625},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.7806806564331055},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.769556999206543},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.7447344660758972},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6756983399391174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6201202869415283},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.6004441976547241},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.5406920313835144},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.43944546580314636},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3803536295890808},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.379216730594635},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3693399727344513},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07430347800254822}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8253366351127625},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.7806806564331055},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.769556999206543},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.7447344660758972},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6756983399391174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6201202869415283},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.6004441976547241},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.5406920313835144},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.43944546580314636},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3803536295890808},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.379216730594635},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3693399727344513},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07430347800254822},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/database/baac074","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baac074","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baac074/46128942/baac074.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},{"id":"pmid:36170114","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36170114","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":"Database : the journal of biological databases and curation","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9518746","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9518746","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,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Database (Oxford)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/database/baac074","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baac074","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baac074/46128942/baac074.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4399999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1623072288","https://openalex.org/W2145870108","https://openalex.org/W2149369282","https://openalex.org/W2346452181","https://openalex.org/W2533611849","https://openalex.org/W2573492843","https://openalex.org/W2765742249","https://openalex.org/W2769387903","https://openalex.org/W2809349863","https://openalex.org/W2890830728","https://openalex.org/W2911489562","https://openalex.org/W3034229721","https://openalex.org/W3034662187","https://openalex.org/W3046375318","https://openalex.org/W3100452049","https://openalex.org/W3104502698","https://openalex.org/W3105491236","https://openalex.org/W3115908473","https://openalex.org/W3137481621","https://openalex.org/W3164540570","https://openalex.org/W3170822064","https://openalex.org/W3217527629","https://openalex.org/W4221142212","https://openalex.org/W4226154421","https://openalex.org/W4226193871","https://openalex.org/W6776534956","https://openalex.org/W6776781563","https://openalex.org/W6779167211","https://openalex.org/W6785110541","https://openalex.org/W6794029143","https://openalex.org/W6804938495","https://openalex.org/W6811330432"],"related_works":["https://openalex.org/W2793132289","https://openalex.org/W3094868181","https://openalex.org/W3116252395","https://openalex.org/W4281560212","https://openalex.org/W3180764077","https://openalex.org/W2769084352","https://openalex.org/W4386322467","https://openalex.org/W4385574021","https://openalex.org/W4254089628","https://openalex.org/W2997394673"],"abstract_inverted_index":{"Chemical":[0],"identification":[1],"involves":[2],"finding":[3],"chemical":[4],"entities":[5,18],"in":[6,43,55,132,151,168,176],"text":[7],"(i.e.":[8,19],"named":[9,20,133,152],"entity":[10,21,134,153],"recognition)":[11],"and":[12,28,34,65,73,84,128,136,143,147,163],"assigning":[13],"unique":[14],"identifiers":[15],"to":[16,62,76],"the":[17,78,95,100,109,117,140,169,173,177],"normalization).":[22],"While":[23],"current":[24],"models":[25,54],"are":[26],"developed":[27],"evaluated":[29],"based":[30],"on":[31],"article":[32],"titles":[33],"abstracts,":[35],"their":[36],"effectiveness":[37],"has":[38],"not":[39],"been":[40],"thoroughly":[41],"verified":[42],"full":[44],"text.":[45],"In":[46,116,155],"this":[47],"paper,":[48],"we":[49,159],"identify":[50],"two":[51],"limitations":[52,79],"of":[53,103,112],"tagging":[56,67],"full-text":[57],"articles:":[58],"(1)":[59],"low":[60],"generalizability":[61],"unseen":[63],"mentions":[64],"(2)":[66],"inconsistency.":[68],"We":[69,88],"use":[70],"simple":[71],"training":[72],"post-processing":[74],"methods":[75],"address":[77],"such":[80],"as":[81],"transfer":[82],"learning":[83],"mention-wise":[85],"majority":[86],"voting.":[87],"also":[89],"present":[90],"a":[91,104,113,156],"hybrid":[92],"model":[93,106,125,162],"for":[94],"normalization":[96,170],"task":[97],"that":[98],"utilizes":[99],"high":[101,110],"recall":[102],"neural":[105],"while":[107],"maintaining":[108],"precision":[111],"dictionary":[114],"model.":[115],"BioCreative":[118],"VII":[119],"NLM-Chem":[120],"track":[121],"challenge,":[122],"our":[123,161],"best":[124,174],"achieves":[126],"86.72":[127],"78.31":[129],"F1":[130,145,166,181],"scores":[131],"recognition":[135],"normalization,":[137],"significantly":[138],"outperforming":[139,172],"median":[141],"(83.73":[142],"77.49":[144],"scores)":[146],"taking":[148],"first":[149],"place":[150],"recognition.":[154],"post-challenge":[157],"evaluation,":[158],"re-implement":[160],"obtain":[164],"84.70":[165],"score":[167,175],"task,":[171],"challenge":[178],"by":[179],"3.34":[180],"score.":[182],"Database":[183],"URL:":[184],"https://github.com/dmis-lab/bc7-chem-id.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
