{"id":"https://openalex.org/W4296783454","doi":"https://doi.org/10.1162/coli_a_00462","title":"Transformers and the Representation of Biomedical Background Knowledge","display_name":"Transformers and the Representation of Biomedical Background Knowledge","publication_year":2022,"publication_date":"2022-09-20","ids":{"openalex":"https://openalex.org/W4296783454","doi":"https://doi.org/10.1162/coli_a_00462"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00462","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00462","pdf_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00462/2062688/coli_a_00462.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00462/2062688/coli_a_00462.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082922366","display_name":"Oskar Wysocki","orcid":"https://orcid.org/0000-0002-7053-4919"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]},{"id":"https://openalex.org/I4210129527","display_name":"Cancer Research UK Manchester Institute","ror":"https://ror.org/037405c78","country_code":"GB","type":"facility","lineage":["https://openalex.org/I2801316944","https://openalex.org/I4210129527"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Oskar Wysocki","raw_affiliation_strings":["Digital Experimental Cancer Medicine Team, Cancer Biomarker Centre, CRUK Manchester Institute, University of Manchester. oskar.wysocki@manchester.ac.uk"],"affiliations":[{"raw_affiliation_string":"Digital Experimental Cancer Medicine Team, Cancer Biomarker Centre, CRUK Manchester Institute, University of Manchester. oskar.wysocki@manchester.ac.uk","institution_ids":["https://openalex.org/I4210129527","https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068884216","display_name":"Zili Zhou","orcid":"https://orcid.org/0000-0002-9223-6269"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Zili Zhou","raw_affiliation_strings":["Department of Computer Science, University of Manchester. zili.zhou@manchester.ac.uk"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Manchester. zili.zhou@manchester.ac.uk","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015115681","display_name":"Paul O\u2019Regan","orcid":"https://orcid.org/0000-0002-0231-5028"},"institutions":[{"id":"https://openalex.org/I4210129527","display_name":"Cancer Research UK Manchester Institute","ror":"https://ror.org/037405c78","country_code":"GB","type":"facility","lineage":["https://openalex.org/I2801316944","https://openalex.org/I4210129527"]},{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Paul O\u2019Regan","raw_affiliation_strings":["Digital Experimental Cancer Medicine Team, Cancer Biomarker Centre, CRUK Manchester Institute, University of Manchester. paul.oregan@digitalecmt.com"],"affiliations":[{"raw_affiliation_string":"Digital Experimental Cancer Medicine Team, Cancer Biomarker Centre, CRUK Manchester Institute, University of Manchester. paul.oregan@digitalecmt.com","institution_ids":["https://openalex.org/I4210129527","https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007420830","display_name":"Deborah Ferreira","orcid":"https://orcid.org/0000-0001-9182-5208"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Deborah Ferreira","raw_affiliation_strings":["Department of Computer Science, University of Manchester. deborah.ferreira@manchester.ac.uk"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Manchester. deborah.ferreira@manchester.ac.uk","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083471294","display_name":"Magdalena Wysocka","orcid":"https://orcid.org/0000-0001-9859-7068"},"institutions":[{"id":"https://openalex.org/I4210129527","display_name":"Cancer Research UK Manchester Institute","ror":"https://ror.org/037405c78","country_code":"GB","type":"facility","lineage":["https://openalex.org/I2801316944","https://openalex.org/I4210129527"]},{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Magdalena Wysocka","raw_affiliation_strings":["Digital Experimental Cancer Medicine Team, Cancer Biomarker Centre, CRUK Manchester Institute, University of Manchester. magdalena.wysocka@digitalecmt.org"],"affiliations":[{"raw_affiliation_string":"Digital Experimental Cancer Medicine Team, Cancer Biomarker Centre, CRUK Manchester Institute, University of Manchester. magdalena.wysocka@digitalecmt.org","institution_ids":["https://openalex.org/I4210129527","https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071160473","display_name":"D\u00f3nal Landers","orcid":"https://orcid.org/0000-0001-8376-9779"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]},{"id":"https://openalex.org/I4210129527","display_name":"Cancer Research UK Manchester Institute","ror":"https://ror.org/037405c78","country_code":"GB","type":"facility","lineage":["https://openalex.org/I2801316944","https://openalex.org/I4210129527"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"D\u00f3nal Landers","raw_affiliation_strings":["Digital Experimental Cancer Medicine Team, Cancer Biomarker Centre, CRUK Manchester Institute, University of Manchester. donal.landers@delondraoncology.com"],"affiliations":[{"raw_affiliation_string":"Digital Experimental Cancer Medicine Team, Cancer Biomarker Centre, CRUK Manchester Institute, University of Manchester. donal.landers@delondraoncology.com","institution_ids":["https://openalex.org/I4210129527","https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053978668","display_name":"Andr\u00e9 Freitas","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Andr\u00e9 Freitas","raw_affiliation_strings":["Idiap Research Institute Martigny, Switzerland. andre.freitas@manchester.ac.uk"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute Martigny, Switzerland. andre.freitas@manchester.ac.uk","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5007420830","https://openalex.org/A5015115681","https://openalex.org/A5053978668","https://openalex.org/A5068884216","https://openalex.org/A5071160473","https://openalex.org/A5082922366","https://openalex.org/A5083471294"],"corresponding_institution_ids":["https://openalex.org/I28407311","https://openalex.org/I4210129527","https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":1.544,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.82891184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"49","issue":"1","first_page":"73","last_page":"115"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9944999814033508,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9860000014305115,"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/computer-science","display_name":"Computer science","score":0.7980921268463135},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.789559006690979},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7499001026153564},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5688738226890564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5311960577964783},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4833197593688965},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45647484064102173},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.43582719564437866},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41673290729522705},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3350503444671631},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.16503804922103882},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11911141872406006}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7980921268463135},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.789559006690979},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7499001026153564},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5688738226890564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5311960577964783},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4833197593688965},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45647484064102173},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.43582719564437866},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41673290729522705},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3350503444671631},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.16503804922103882},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11911141872406006},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/coli_a_00462","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00462","pdf_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00462/2062688/coli_a_00462.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2bf6fc1e84d4479fa9c42e7f0b2a4453","is_oa":true,"landing_page_url":"https://doaj.org/article/2bf6fc1e84d4479fa9c42e7f0b2a4453","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 49, Iss 1 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00462","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00462","pdf_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00462/2062688/coli_a_00462.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4296783454.pdf","grobid_xml":"https://content.openalex.org/works/W4296783454.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W1967320885","https://openalex.org/W2129415103","https://openalex.org/W2167179525","https://openalex.org/W2515741950","https://openalex.org/W2559034752","https://openalex.org/W2566723262","https://openalex.org/W2583911935","https://openalex.org/W2601243251","https://openalex.org/W2614443510","https://openalex.org/W2619824656","https://openalex.org/W2826721128","https://openalex.org/W2886342253","https://openalex.org/W2888041867","https://openalex.org/W2889326414","https://openalex.org/W2895954017","https://openalex.org/W2896448590","https://openalex.org/W2911489562","https://openalex.org/W2951286828","https://openalex.org/W2962736243","https://openalex.org/W2962859618","https://openalex.org/W2963969878","https://openalex.org/W2964242047","https://openalex.org/W2969524309","https://openalex.org/W2980495554","https://openalex.org/W2989891169","https://openalex.org/W2993172114","https://openalex.org/W2997402146","https://openalex.org/W3011643984","https://openalex.org/W3035305735","https://openalex.org/W3035352537","https://openalex.org/W3037888463","https://openalex.org/W3100355250","https://openalex.org/W3100879603","https://openalex.org/W3103368673","https://openalex.org/W3104578551","https://openalex.org/W3144750446","https://openalex.org/W3146944767","https://openalex.org/W3161121057","https://openalex.org/W3166593409","https://openalex.org/W3166986030","https://openalex.org/W3171832821","https://openalex.org/W3173944183","https://openalex.org/W3174088532","https://openalex.org/W3176477796","https://openalex.org/W3201490839","https://openalex.org/W3202070718","https://openalex.org/W3205235328","https://openalex.org/W4210658956","https://openalex.org/W4226153908","https://openalex.org/W4285175792","https://openalex.org/W4287366208","https://openalex.org/W6726295259","https://openalex.org/W6790370217","https://openalex.org/W6802712164","https://openalex.org/W6810928796"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W4206178588","https://openalex.org/W4287635093","https://openalex.org/W3094491777","https://openalex.org/W3214715529"],"abstract_inverted_index":{"Abstract":[0],"Specialized":[1],"transformers-based":[2],"models":[3,109,131],"(such":[4],"as":[5],"BioBERT":[6],"and":[7,36,44,84,91,103,137],"BioMegatron)":[8],"are":[9],"adapted":[10],"for":[11,81,99,123],"the":[12,25,34,55,58,66,77,93,97,130,140],"biomedical":[13,19],"domain":[14],"based":[15],"on":[16],"publicly":[17],"available":[18],"corpora.":[20],"As":[21],"such,":[22],"they":[23],"have":[24],"potential":[26,46],"to":[27,48,75,89,135],"encode":[28,112],"large-scale":[29],"biological":[30,39,113],"knowledge.":[31],"We":[32,64,105],"investigate":[33],"encoding":[35],"representation":[37],"of":[38,57,61,68,79,96,117],"knowledge":[40],"in":[41,51,121,139],"these":[42,108],"models,":[43],"its":[45],"utility":[47],"support":[49],"inference":[50],"cancer":[52],"precision":[53],"medicine\u2014namely,":[54],"interpretation":[56],"clinical":[59],"significance":[60],"genomic":[62],"alterations.":[63],"compare":[65,90],"performance":[67],"different":[69],"transformer":[70],"baselines;":[71],"we":[72,85,127],"use":[73,86],"probing":[74],"determine":[76],"consistency":[78],"encodings":[80],"distinct":[82],"entities;":[83],"clustering":[87],"methods":[88],"contrast":[92],"internal":[94],"properties":[95],"embeddings":[98],"genes,":[100],"variants,":[101],"drugs,":[102],"diseases.":[104],"show":[106],"that":[107],"do":[110],"indeed":[111],"knowledge,":[114],"although":[115],"some":[116],"this":[118],"is":[119],"lost":[120],"fine-tuning":[122],"specific":[124],"tasks.":[125],"Finally,":[126],"analyze":[128],"how":[129],"behave":[132],"with":[133],"regard":[134],"biases":[136],"imbalances":[138],"dataset.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
