{"id":"https://openalex.org/W2904867915","doi":"https://doi.org/10.1186/s13321-018-0313-8","title":"Chemlistem: chemical named entity recognition using recurrent neural networks","display_name":"Chemlistem: chemical named entity recognition using recurrent neural networks","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2904867915","doi":"https://doi.org/10.1186/s13321-018-0313-8","mag":"2904867915","pmid":"https://pubmed.ncbi.nlm.nih.gov/30523437"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-018-0313-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-018-0313-8","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13321-018-0313-8.pdf","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://link.springer.com/content/pdf/10.1186/s13321-018-0313-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056067513","display_name":"Peter Corbett","orcid":"https://orcid.org/0000-0002-3029-8325"},"institutions":[{"id":"https://openalex.org/I1289762815","display_name":"Royal Society","ror":"https://ror.org/03wnrjx87","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I1289762815"]},{"id":"https://openalex.org/I2751430930","display_name":"Royal Society of Chemistry","ror":"https://ror.org/025sbr097","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2751430930"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Peter Corbett","raw_affiliation_strings":["Data Science Group, Technology Department, The Royal Society of Chemistry, Cambridge, UK. corbettp@rsc.org","Data Science Group, Technology Department, The Royal Society of Chemistry, Cambridge, UK"],"raw_orcid":"https://orcid.org/0000-0002-3029-8325","affiliations":[{"raw_affiliation_string":"Data Science Group, Technology Department, The Royal Society of Chemistry, Cambridge, UK. corbettp@rsc.org","institution_ids":["https://openalex.org/I2751430930","https://openalex.org/I1289762815"]},{"raw_affiliation_string":"Data Science Group, Technology Department, The Royal Society of Chemistry, Cambridge, UK","institution_ids":["https://openalex.org/I2751430930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056677361","display_name":"John Boyle","orcid":"https://orcid.org/0000-0002-5378-5361"},"institutions":[{"id":"https://openalex.org/I2751430930","display_name":"Royal Society of Chemistry","ror":"https://ror.org/025sbr097","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2751430930"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"John Boyle","raw_affiliation_strings":["Data Science Group, Technology Department, The Royal Society of Chemistry, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Science Group, Technology Department, The Royal Society of Chemistry, Cambridge, UK","institution_ids":["https://openalex.org/I2751430930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056067513"],"corresponding_institution_ids":["https://openalex.org/I1289762815","https://openalex.org/I2751430930"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":3.8859,"has_fulltext":true,"cited_by_count":53,"citation_normalized_percentile":{"value":0.94839253,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"10","issue":"1","first_page":"59","last_page":"59"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9968000054359436,"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":0.9968000054359436,"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":0.9858999848365784,"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":0.9736999869346619,"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":0.8084352016448975},{"id":"https://openalex.org/keywords/crfs","display_name":"CRFS","score":0.7785438895225525},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.7167259454727173},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7074161171913147},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.6940019726753235},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6118601560592651},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5745868682861328},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5424173474311829},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5315541625022888},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5248967409133911},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5217062830924988},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47577348351478577},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47508326172828674},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46344852447509766},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4628893733024597},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4396059215068817},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37713488936424255},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.12485203146934509}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8084352016448975},{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.7785438895225525},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.7167259454727173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7074161171913147},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.6940019726753235},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6118601560592651},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5745868682861328},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5424173474311829},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5315541625022888},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5248967409133911},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5217062830924988},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47577348351478577},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47508326172828674},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46344852447509766},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4628893733024597},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4396059215068817},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37713488936424255},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.12485203146934509},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-018-0313-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-018-0313-8","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13321-018-0313-8.pdf","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:30523437","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30523437","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:doaj.org/article:3db54c543409447bae75cca84c4862e7","is_oa":true,"landing_page_url":"https://doaj.org/article/3db54c543409447bae75cca84c4862e7","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,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 10, Iss 1, Pp 1-9 (2018)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:6755713","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6755713","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":"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/s13321-018-0313-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-018-0313-8","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13321-018-0313-8.pdf","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":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2904867915.pdf","grobid_xml":"https://content.openalex.org/works/W2904867915.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2033377040","https://openalex.org/W2049240985","https://openalex.org/W2101234009","https://openalex.org/W2104071081","https://openalex.org/W2127239015","https://openalex.org/W2158899491","https://openalex.org/W2165671627","https://openalex.org/W2165698076","https://openalex.org/W2169491861","https://openalex.org/W2250539671","https://openalex.org/W2395579298","https://openalex.org/W2606347107","https://openalex.org/W2771371538","https://openalex.org/W2775645290","https://openalex.org/W2883749461","https://openalex.org/W2919115771","https://openalex.org/W2950577311","https://openalex.org/W6600654476"],"related_works":["https://openalex.org/W1964783010","https://openalex.org/W4250494529","https://openalex.org/W2399696375","https://openalex.org/W2061834489","https://openalex.org/W3088215229","https://openalex.org/W182104056","https://openalex.org/W45206245","https://openalex.org/W50079190","https://openalex.org/W2534386351","https://openalex.org/W11196620"],"abstract_inverted_index":{"Chemical":[0],"named":[1,44],"entity":[2,45],"recognition":[3,46],"(NER)":[4],"has":[5],"traditionally":[6],"been":[7],"dominated":[8],"by":[9],"conditional":[10],"random":[11],"fields":[12],"(CRF)-based":[13],"approaches":[14],"but":[15],"given":[16],"the":[17,20,52,92,118,121,134,138,156],"success":[18],"of":[19,73,84,99,120,153],"artificial":[21],"neural":[22,66,86,103],"network":[23],"techniques":[24],"known":[25],"as":[26,34],"\"deep":[27],"learning\"":[28],"we":[29],"decided":[30],"to":[31,37],"examine":[32],"them":[33],"an":[35,114],"alternative":[36],"CRFs.":[38],"We":[39],"present":[40],"here":[41],"several":[42],"chemical":[43],"systems.":[47,124],"The":[48,88,110],"first":[49,122],"system":[50,90,112],"translates":[51],"traditional":[53],"CRF-based":[54],"idioms":[55],"into":[56],"a":[57,71,149],"deep":[58],"learning":[59,146],"framework,":[60],"using":[61,75,102,144],"rich":[62,93],"per-token":[63],"features":[64],"and":[65,69,106,142],"word":[67],"embeddings,":[68],"producing":[70],"sequence":[72],"tags":[74],"bidirectional":[76],"long":[77],"short":[78],"term":[79],"memory":[80],"(LSTM)":[81],"networks-a":[82],"type":[83],"recurrent":[85],"net.":[87],"second":[89],"eschews":[91],"feature":[94],"set-and":[95],"even":[96],"tokenisation-in":[97],"favour":[98],"character":[100,104],"labelling":[101],"embeddings":[105],"multiple":[107],"LSTM":[108],"layers.":[109],"third":[111],"is":[113],"ensemble":[115],"that":[116],"combines":[117],"results":[119],"two":[123],"Our":[125],"original":[126],"BioCreative":[127],"V.5":[128],"competition":[129],"entry":[130],"was":[131],"placed":[132],"in":[133],"top":[135],"group":[136],"with":[137],"highest":[139],"F":[140,151],"scores,":[141],"subsequent":[143],"transfer":[145],"have":[147],"achieved":[148],"final":[150],"score":[152],"90.33%":[154],"on":[155],"test":[157],"data":[158],"(precision":[159],"91.47%,":[160],"recall":[161],"89.21%).":[162]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}