{"id":"https://openalex.org/W2887377541","doi":"https://doi.org/10.18653/v1/w18-2307","title":"Sub-word information in pre-trained biomedical word representations: evaluation and hyper-parameter optimization","display_name":"Sub-word information in pre-trained biomedical word representations: evaluation and hyper-parameter optimization","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2887377541","doi":"https://doi.org/10.18653/v1/w18-2307","mag":"2887377541"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-2307","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-2307","pdf_url":"https://www.aclweb.org/anthology/W18-2307.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the BioNLP 2018 workshop","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-2307.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011362662","display_name":"Dieter Galea","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dieter Galea","raw_affiliation_strings":["Department of Surgery and Cancer","Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Surgery and Cancer","institution_ids":[]},{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050041550","display_name":"Ivan Laponogov","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ivan Laponogov","raw_affiliation_strings":["Department of Surgery and Cancer","Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Surgery and Cancer","institution_ids":[]},{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061524521","display_name":"Kirill Veselkov","orcid":"https://orcid.org/0000-0002-1164-0359"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kirill Veselkov","raw_affiliation_strings":["Department of Surgery and Cancer","Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Surgery and Cancer","institution_ids":[]},{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.4527,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.66495233,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"56","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9987000226974487,"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":0.998199999332428,"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/word2vec","display_name":"Word2vec","score":0.9418872594833374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8109142780303955},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7589049935340881},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6702831387519836},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6338306665420532},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6318272352218628},{"id":"https://openalex.org/keywords/principle-of-compositionality","display_name":"Principle of compositionality","score":0.6160341501235962},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5098918676376343},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4810955226421356},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.45403218269348145},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4159519076347351},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11198511719703674}],"concepts":[{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.9418872594833374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8109142780303955},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7589049935340881},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6702831387519836},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6338306665420532},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6318272352218628},{"id":"https://openalex.org/C121375916","wikidata":"https://www.wikidata.org/wiki/Q936559","display_name":"Principle of compositionality","level":2,"score":0.6160341501235962},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5098918676376343},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4810955226421356},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.45403218269348145},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4159519076347351},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11198511719703674},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w18-2307","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-2307","pdf_url":"https://www.aclweb.org/anthology/W18-2307.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the BioNLP 2018 workshop","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-2307","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-2307","pdf_url":"https://www.aclweb.org/anthology/W18-2307.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the BioNLP 2018 workshop","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7200000286102295}],"awards":[{"id":"https://openalex.org/G5827216101","display_name":"Development of a rapid bacterial identification method based on direct mass spectrometric metabolic profiling","funder_award_id":"BB/L020858/1","funder_id":"https://openalex.org/F4320334629","funder_display_name":"Biotechnology and Biological Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320283","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10"},{"id":"https://openalex.org/F4320334629","display_name":"Biotechnology and Biological Sciences Research Council","ror":"https://ror.org/00cwqg982"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2887377541.pdf","grobid_xml":"https://content.openalex.org/works/W2887377541.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W168564468","https://openalex.org/W1832693441","https://openalex.org/W1905278307","https://openalex.org/W1971220772","https://openalex.org/W2037382435","https://openalex.org/W2047782770","https://openalex.org/W2136480620","https://openalex.org/W2145870108","https://openalex.org/W2153579005","https://openalex.org/W2154142897","https://openalex.org/W2159092541","https://openalex.org/W2250539671","https://openalex.org/W2296283641","https://openalex.org/W2493916176","https://openalex.org/W2509406088","https://openalex.org/W2515248967","https://openalex.org/W2515910099","https://openalex.org/W2527896214","https://openalex.org/W2613831280","https://openalex.org/W2757849489","https://openalex.org/W2769387903","https://openalex.org/W2780932362","https://openalex.org/W2783212081","https://openalex.org/W2791951321","https://openalex.org/W2962681409","https://openalex.org/W2962772361","https://openalex.org/W2962986031","https://openalex.org/W2963419157","https://openalex.org/W2963421945","https://openalex.org/W3208472798","https://openalex.org/W4294170691","https://openalex.org/W4294367149"],"related_works":["https://openalex.org/W3095531775","https://openalex.org/W1526190050","https://openalex.org/W2905749112","https://openalex.org/W1997182898","https://openalex.org/W2346530426","https://openalex.org/W3099354896","https://openalex.org/W2890749918","https://openalex.org/W4287599800","https://openalex.org/W2772765860","https://openalex.org/W4312264180"],"abstract_inverted_index":{"Word2vec":[0],"embeddings":[1,97],"are":[2],"limited":[3],"to":[4,39,59,89],"computing":[5],"vectors":[6],"for":[7,32,48],"in-vocabulary":[8],"terms":[9],"and":[10,28,53,116,119],"do":[11],"not":[12],"take":[13],"into":[14],"account":[15],"sub-word":[16],"information.":[17],"Characterbased":[18],"representations,":[19],"such":[20,24,50,74],"as":[21,51,67,69],"fastText,":[22],"mitigate":[23],"limitations.":[25],"We":[26,107],"optimize":[27],"compare":[29],"these":[30],"representations":[31],"the":[33,70,103],"biomedical":[34],"domain.":[35],"fastText":[36,120],"was":[37],"found":[38],"consistently":[40],"outperform":[41],"word2vec":[42,118],"in":[43,91],"named":[44],"entity":[45],"recognition":[46],"tasks":[47],"entities":[49],"chemicals":[52],"genes.":[54],"This":[55,95],"is":[56],"likely":[57,87],"due":[58,88],"gained":[60],"information":[61],"from":[62],"computed":[63],"out-of-vocabulary":[64],"term":[65,92],"vectors,":[66],"well":[68],"word":[71],"compositionality":[72],"of":[73,112],"entities.":[75],"Contrastingly,":[76],"performance":[77],"varied":[78],"on":[79,102,123],"intrinsic":[80,85],"datasets.":[81],"Optimal":[82],"hyper-parameters":[83],"were":[84],"dataset-dependent,":[86],"differences":[90],"types":[93],"distributions.":[94],"indicates":[96],"should":[98],"be":[99],"chosen":[100],"based":[101],"task":[104],"at":[105],"hand.":[106],"therefore":[108],"provide":[109],"a":[110],"number":[111],"optimized":[113],"hyper-parameter":[114],"sets":[115],"pretrained":[117],"models,":[121],"available":[122],"https://github.com/dterg/bionlpembed.":[124]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}