{"id":"https://openalex.org/W2515248967","doi":"https://doi.org/10.18653/v1/w16-2922","title":"How to Train good Word Embeddings for Biomedical NLP","display_name":"How to Train good Word Embeddings for Biomedical NLP","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2515248967","doi":"https://doi.org/10.18653/v1/w16-2922","mag":"2515248967"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w16-2922","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2922","pdf_url":"https://www.aclweb.org/anthology/W16-2922.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 15th Workshop on Biomedical Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W16-2922.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024945225","display_name":"Billy Chiu","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210107233","display_name":"Language Science (South Korea)","ror":"https://ror.org/01h9v1373","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210107233"]}],"countries":["GB","KR"],"is_corresponding":true,"raw_author_name":"Billy Chiu","raw_affiliation_strings":["Language Technology Lab DTAL, University of Cambridge"],"affiliations":[{"raw_affiliation_string":"Language Technology Lab DTAL, University of Cambridge","institution_ids":["https://openalex.org/I4210107233","https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090932014","display_name":"Gamal Crichton","orcid":"https://orcid.org/0000-0002-3036-0811"},"institutions":[{"id":"https://openalex.org/I4210107233","display_name":"Language Science (South Korea)","ror":"https://ror.org/01h9v1373","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210107233"]},{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB","KR"],"is_corresponding":false,"raw_author_name":"Gamal Crichton","raw_affiliation_strings":["Language Technology Lab DTAL, University of Cambridge"],"affiliations":[{"raw_affiliation_string":"Language Technology Lab DTAL, University of Cambridge","institution_ids":["https://openalex.org/I4210107233","https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081393566","display_name":"Anna Korhonen","orcid":"https://orcid.org/0000-0002-3692-3144"},"institutions":[{"id":"https://openalex.org/I4210107233","display_name":"Language Science (South Korea)","ror":"https://ror.org/01h9v1373","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210107233"]},{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB","KR"],"is_corresponding":false,"raw_author_name":"Anna Korhonen","raw_affiliation_strings":["Language Technology Lab DTAL, University of Cambridge"],"affiliations":[{"raw_affiliation_string":"Language Technology Lab DTAL, University of Cambridge","institution_ids":["https://openalex.org/I4210107233","https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066925770","display_name":"Sampo Pyysalo","orcid":"https://orcid.org/0000-0002-6279-5000"},"institutions":[{"id":"https://openalex.org/I4210107233","display_name":"Language Science (South Korea)","ror":"https://ror.org/01h9v1373","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210107233"]},{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB","KR"],"is_corresponding":false,"raw_author_name":"Sampo Pyysalo","raw_affiliation_strings":["Language Technology Lab DTAL, University of Cambridge"],"affiliations":[{"raw_affiliation_string":"Language Technology Lab DTAL, University of Cambridge","institution_ids":["https://openalex.org/I4210107233","https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5024945225"],"corresponding_institution_ids":["https://openalex.org/I241749","https://openalex.org/I4210107233"],"apc_list":null,"apc_paid":null,"fwci":65.319,"has_fulltext":true,"cited_by_count":354,"citation_normalized_percentile":{"value":0.99882028,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"166","last_page":"174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7687397599220276},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7687064409255981},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7461702227592468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.730574369430542},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39173561334609985},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15636804699897766}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7687397599220276},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7687064409255981},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7461702227592468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.730574369430542},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39173561334609985},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15636804699897766},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w16-2922","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2922","pdf_url":"https://www.aclweb.org/anthology/W16-2922.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 15th Workshop on Biomedical Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w16-2922","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2922","pdf_url":"https://www.aclweb.org/anthology/W16-2922.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 15th Workshop on Biomedical Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4293880762","display_name":null,"funder_award_id":"MR/M013049","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"},{"id":"https://openalex.org/G4498546091","display_name":"Literature-based discovery for cancer biology","funder_award_id":"MR/M013049/1","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"}],"funders":[{"id":"https://openalex.org/F4320334626","display_name":"Medical Research Council","ror":"https://ror.org/03x94j517"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2515248967.pdf","grobid_xml":"https://content.openalex.org/works/W2515248967.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W83139929","https://openalex.org/W202767273","https://openalex.org/W1614298861","https://openalex.org/W1615991656","https://openalex.org/W1854884267","https://openalex.org/W2047782770","https://openalex.org/W2117130368","https://openalex.org/W2143017621","https://openalex.org/W2153579005","https://openalex.org/W2154142897","https://openalex.org/W2158139315","https://openalex.org/W2250539671","https://openalex.org/W2251157338","https://openalex.org/W2251243116","https://openalex.org/W2290054636","https://openalex.org/W2515910099","https://openalex.org/W2527896214","https://openalex.org/W2953320089","https://openalex.org/W2998704965","https://openalex.org/W3099386342","https://openalex.org/W4285719527","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655","https://openalex.org/W2359140296"],"abstract_inverted_index":{"The":[0],"quality":[1,36],"of":[2,33,37],"word":[3,77,92],"embeddings":[4,38,93],"depends":[5],"on":[6],"the":[7,16,35,47,89],"input":[8],"corpora,":[9],"model":[10],"architectures,":[11],"and":[12,22,25,61,84],"hyper-parameter":[13],"settings.":[14],"Using":[15],"state-of-the-art":[17,91],"neural":[18],"embedding":[19],"tool":[20],"word2vec":[21],"both":[23],"intrinsic":[24,60],"extrinsic":[26,62],"evaluations,":[27],"we":[28,51,65],"present":[29],"a":[30],"comprehensive":[31],"study":[32],"how":[34],"changes":[39],"according":[40],"to":[41],"these":[42],"features.":[43],"Apart":[44],"from":[45,98],"identifying":[46],"most":[48],"influential":[49],"hyper-parameters,":[50],"also":[52],"observe":[53],"one":[54],"that":[55,67],"creates":[56],"contradictory":[57],"results":[58],"between":[59],"evaluations.":[63],"Furthermore,":[64],"find":[66],"bigger":[68],"corpora":[69],"do":[70],"not":[71],"necessarily":[72],"produce":[73],"better":[74],"biomedical":[75],"domain":[76],"embeddings.":[78],"We":[79],"make":[80],"our":[81],"evaluation":[82],"tools":[83],"resources":[85],"as":[86,88],"well":[87],"created":[90],"available":[94],"under":[95],"open":[96],"licenses":[97],"https://github.com/":[99],"cambridgeltl/BioNLP-2016.":[100]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":26},{"year":2022,"cited_by_count":31},{"year":2021,"cited_by_count":48},{"year":2020,"cited_by_count":74},{"year":2019,"cited_by_count":86},{"year":2018,"cited_by_count":42},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":2}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}