{"id":"https://openalex.org/W4389543134","doi":"https://doi.org/10.1109/embc40787.2023.10340499","title":"Masked Language Modeling for Resource Constrained Biological Natural Language Processing","display_name":"Masked Language Modeling for Resource Constrained Biological Natural Language Processing","publication_year":2023,"publication_date":"2023-07-24","ids":{"openalex":"https://openalex.org/W4389543134","doi":"https://doi.org/10.1109/embc40787.2023.10340499","pmid":"https://pubmed.ncbi.nlm.nih.gov/38083556"},"language":"en","primary_location":{"id":"doi:10.1109/embc40787.2023.10340499","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/embc40787.2023.10340499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077532815","display_name":"Haasha Bin Atif","orcid":"https://orcid.org/0009-0008-7498-9727"},"institutions":[{"id":"https://openalex.org/I201384688","display_name":"National University of Computer and Emerging Sciences","ror":"https://ror.org/003eyb898","country_code":"PK","type":"education","lineage":["https://openalex.org/I201384688"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Haasha Bin Atif","raw_affiliation_strings":["National University of Computer and Emerging Sciences,Islamabad,Pakistan","National University of Computer and Emerging Sciences, Islamabad, Pakistan"],"affiliations":[{"raw_affiliation_string":"National University of Computer and Emerging Sciences,Islamabad,Pakistan","institution_ids":["https://openalex.org/I201384688"]},{"raw_affiliation_string":"National University of Computer and Emerging Sciences, Islamabad, Pakistan","institution_ids":["https://openalex.org/I201384688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089584963","display_name":"Hamza Mustafa Alvi","orcid":"https://orcid.org/0000-0001-6306-8131"},"institutions":[{"id":"https://openalex.org/I201384688","display_name":"National University of Computer and Emerging Sciences","ror":"https://ror.org/003eyb898","country_code":"PK","type":"education","lineage":["https://openalex.org/I201384688"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Hamza Alvi","raw_affiliation_strings":["National University of Computer and Emerging Sciences,Islamabad,Pakistan","National University of Computer and Emerging Sciences, Islamabad, Pakistan"],"affiliations":[{"raw_affiliation_string":"National University of Computer and Emerging Sciences,Islamabad,Pakistan","institution_ids":["https://openalex.org/I201384688"]},{"raw_affiliation_string":"National University of Computer and Emerging Sciences, Islamabad, Pakistan","institution_ids":["https://openalex.org/I201384688"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074736458","display_name":"Hammad Naveed","orcid":"https://orcid.org/0000-0002-1867-974X"},"institutions":[{"id":"https://openalex.org/I201384688","display_name":"National University of Computer and Emerging Sciences","ror":"https://ror.org/003eyb898","country_code":"PK","type":"education","lineage":["https://openalex.org/I201384688"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Hammad Naveed","raw_affiliation_strings":["National University of Computer and Emerging Sciences,Islamabad,Pakistan","National University of Computer and Emerging Sciences, Islamabad, Pakistan"],"affiliations":[{"raw_affiliation_string":"National University of Computer and Emerging Sciences,Islamabad,Pakistan","institution_ids":["https://openalex.org/I201384688"]},{"raw_affiliation_string":"National University of Computer and Emerging Sciences, Islamabad, Pakistan","institution_ids":["https://openalex.org/I201384688"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077532815"],"corresponding_institution_ids":["https://openalex.org/I201384688"],"apc_list":null,"apc_paid":null,"fwci":0.3086,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64992098,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"2023","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9997000098228455,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9997000098228455,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9976000189781189,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9973000288009644,"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":0.7972260117530823},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.6537810564041138},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.65311199426651},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.6376323699951172},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.576907217502594},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5759260058403015},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5428585410118103},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5033065676689148},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48711419105529785},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4819033443927765},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.45812568068504333},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.44595223665237427},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41856345534324646},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2566260099411011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7972260117530823},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.6537810564041138},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.65311199426651},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.6376323699951172},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.576907217502594},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5759260058403015},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5428585410118103},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5033065676689148},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48711419105529785},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4819033443927765},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.45812568068504333},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.44595223665237427},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41856345534324646},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2566260099411011},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017432","descriptor_name":"Unified Medical Language System","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017432","descriptor_name":"Unified Medical Language System","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017432","descriptor_name":"Unified Medical Language System","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017432","descriptor_name":"Unified Medical Language System","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017432","descriptor_name":"Unified Medical Language System","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/embc40787.2023.10340499","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/embc40787.2023.10340499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)","raw_type":"proceedings-article"},{"id":"pmid:38083556","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38083556","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":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1575935487","https://openalex.org/W1605300833","https://openalex.org/W1998490996","https://openalex.org/W2007989143","https://openalex.org/W2008708467","https://openalex.org/W2049695588","https://openalex.org/W2069700014","https://openalex.org/W2090979435","https://openalex.org/W2097606916","https://openalex.org/W2103017472","https://openalex.org/W2117640066","https://openalex.org/W2128653811","https://openalex.org/W2129588870","https://openalex.org/W2130479394","https://openalex.org/W2153153865","https://openalex.org/W2160050027","https://openalex.org/W2162061564","https://openalex.org/W2250539671","https://openalex.org/W2433743436","https://openalex.org/W2535071049","https://openalex.org/W2554617421","https://openalex.org/W2558841060","https://openalex.org/W2592864539","https://openalex.org/W2595551253","https://openalex.org/W2739202500","https://openalex.org/W2741609678","https://openalex.org/W2742229469","https://openalex.org/W2765779130","https://openalex.org/W2791790018","https://openalex.org/W2888495466","https://openalex.org/W2951433247","https://openalex.org/W2962739339","https://openalex.org/W2963457143","https://openalex.org/W2969644707","https://openalex.org/W2970430411","https://openalex.org/W3043901899","https://openalex.org/W3110645309","https://openalex.org/W3146944767","https://openalex.org/W4297796913","https://openalex.org/W6636510571","https://openalex.org/W6679333912","https://openalex.org/W6683557909","https://openalex.org/W6734247333","https://openalex.org/W6734394903","https://openalex.org/W6755207826","https://openalex.org/W6763868836"],"related_works":["https://openalex.org/W2980729574","https://openalex.org/W1560851690","https://openalex.org/W3092047717","https://openalex.org/W4390881630","https://openalex.org/W2770162183","https://openalex.org/W3110772647","https://openalex.org/W2947721150","https://openalex.org/W2894231409","https://openalex.org/W4205820553","https://openalex.org/W2251441308"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,22,80],"Natural":[3],"Language":[4,127],"Processing":[5],"(NLP)":[6],"have":[7,28],"produced":[8],"state":[9],"of":[10,55,62,75,91,107,146,155,175,178,184],"the":[11,53,73,86,105,108,173,176,182,185],"art":[12],"results":[13],"on":[14,32,140,148,157,168,181],"several":[15],"sequence":[16,18],"to":[17,115,171],"(seq2seq)":[19],"tasks.":[20,34],"Enhancements":[21],"embedders":[23],"and":[24,94,119],"their":[25],"training":[26],"methodologies":[27],"shown":[29],"significant":[30,133],"improvement":[31],"downstream":[33,142,169],"Word":[35],"vector":[36,92],"models":[37],"like":[38],"Word2Vec,":[39],"FastText":[40],"&":[41,153],"Glove":[42],"were":[43],"widely":[44],"used":[45],"over":[46],"one-hot":[47],"encoded":[48],"vectors":[49],"for":[50,97],"years":[51],"until":[52],"advent":[54],"deep":[56],"contextualized":[57],"embedders.":[58],"Protein":[59],"sequences":[60,114],"consist":[61],"20":[63],"naturally":[64],"occurring":[65],"amino":[66,78],"acids":[67,79],"that":[68,131],"can":[69],"be":[70],"treated":[71],"as":[72],"language":[74],"nature.":[76],"These":[77],"combinations":[81],"with":[82],"each":[83],"other":[84],"makeup":[85],"biological":[87,99,179],"functions.":[88],"The":[89],"choice":[90],"representation":[93],"architecture":[95],"design":[96],"a":[98,117],"task":[100,180],"is":[101],"highly":[102],"dependent":[103],"upon":[104],"nature":[106,177],"task.":[109],"We":[110,163],"utilize":[111],"unlabelled":[112],"protein":[113],"train":[116],"Convolution":[118],"Gated":[120],"Recurrent":[121],"Network":[122],"(CGRN)":[123],"embedder":[124],"using":[125],"Masked":[126],"Modeling":[128],"(MLM)":[129],"technique":[130],"shows":[132],"performance":[134,183],"boost":[135],"under":[136],"resource":[137],"constraint":[138],"setting":[139],"two":[141],"tasks":[143,170],"i.e.,":[144],"F1-score(Q8)":[145],"73.1%":[147],"Secondary":[149],"Structure":[150],"Prediction":[151,161],"(SSP)":[152],"F1-score":[154],"84%":[156],"Intrinsically":[158],"Disordered":[159],"Region":[160],"(IDRP).":[162],"also":[164],"compare":[165],"different":[166],"architectures":[167],"show":[172],"impact":[174],"model.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}