{"id":"https://openalex.org/W4285214521","doi":"https://doi.org/10.18653/v1/2022.bionlp-1.6","title":"Data Augmentation for Biomedical Factoid Question Answering","display_name":"Data Augmentation for Biomedical Factoid Question Answering","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285214521","doi":"https://doi.org/10.18653/v1/2022.bionlp-1.6"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.bionlp-1.6","doi":"https://doi.org/10.18653/v1/2022.bionlp-1.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.bionlp-1.6","pdf_url":"https://aclanthology.org/2022.bionlp-1.6.pdf","source":{"id":"https://openalex.org/S7407086806","display_name":"Workshop on Biomedical Language Processing (BioNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 21st Workshop on Biomedical Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2022.bionlp-1.6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001794274","display_name":"Dimitris Pappas","orcid":"https://orcid.org/0000-0001-5784-0658","observed_orcids":["https://orcid.org/0000-0001-5784-0658"]},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]},{"id":"https://openalex.org/I73142707","display_name":"Athens University of Economics and Business","ror":"https://ror.org/03s262162","country_code":"GR","type":"education","lineage":["https://openalex.org/I73142707"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Dimitris Pappas","raw_affiliation_strings":["Department of Informatics, Athens University of Economics and Business, Greece","Institute for Language and Speech Processing, Research Center 'Athena', Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Athens University of Economics and Business, Greece","institution_ids":["https://openalex.org/I73142707"]},{"raw_affiliation_string":"Institute for Language and Speech Processing, Research Center 'Athena', Greece","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016618602","display_name":"Prodromos Malakasiotis","orcid":"https://orcid.org/0009-0008-0055-5598","observed_orcids":["https://orcid.org/0009-0008-0055-5598"]},"institutions":[{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]},{"id":"https://openalex.org/I4387152169","display_name":"Institute of Informatics & Telecommunications","ror":"https://ror.org/0396t6k89","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]},{"id":"https://openalex.org/I73142707","display_name":"Athens University of Economics and Business","ror":"https://ror.org/03s262162","country_code":"GR","type":"education","lineage":["https://openalex.org/I73142707"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Prodromos Malakasiotis","raw_affiliation_strings":["Department of Informatics, Athens University of Economics and Business, Greece","Institute of Informatics and Telecommunications, NCSR 'Demokritos', Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Athens University of Economics and Business, Greece","institution_ids":["https://openalex.org/I73142707"]},{"raw_affiliation_string":"Institute of Informatics and Telecommunications, NCSR 'Demokritos', Greece","institution_ids":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069270736","display_name":"Ion Androutsopoulos","orcid":"https://orcid.org/0009-0000-2969-0509","observed_orcids":["https://orcid.org/0009-0000-2969-0509"]},"institutions":[{"id":"https://openalex.org/I73142707","display_name":"Athens University of Economics and Business","ror":"https://ror.org/03s262162","country_code":"GR","type":"education","lineage":["https://openalex.org/I73142707"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Ion Androutsopoulos","raw_affiliation_strings":["Department of Informatics, Athens University of Economics and Business, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Athens University of Economics and Business, Greece","institution_ids":["https://openalex.org/I73142707"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5001794274"],"corresponding_institution_ids":["https://openalex.org/I4210098364","https://openalex.org/I73142707"],"apc_list":null,"apc_paid":null,"fwci":1.9905,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.89499311,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"63","last_page":"81"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9526000022888184,"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":0.9526000022888184,"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":0.014100000262260437,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.00800000037997961,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/data-augmentation","display_name":"data augmentation","score":0.996999979019165},{"id":"https://openalex.org/keywords/factoid-question-answering","display_name":"factoid question answering","score":0.9589999914169312},{"id":"https://openalex.org/keywords/biomedical-question-answering","display_name":"biomedical question answering","score":0.9890000224113464},{"id":"https://openalex.org/keywords/bioasq","display_name":"BioASQ","score":0.8140000104904175},{"id":"https://openalex.org/keywords/machine-reading-comprehension","display_name":"machine reading comprehension","score":0.7509999871253967},{"id":"https://openalex.org/keywords/back-translation","display_name":"back-translation","score":0.9570000171661377},{"id":"https://openalex.org/keywords/word-substitution","display_name":"word substitution","score":0.7129999995231628},{"id":"https://openalex.org/keywords/word2vec-embeddings","display_name":"Word2Vec embeddings","score":0.9300000071525574},{"id":"https://openalex.org/keywords/question-generation","display_name":"question generation","score":0.7710000276565552},{"id":"https://openalex.org/keywords/pre-trained-transformers","display_name":"pre-trained transformer models","score":0.5740000009536743},{"id":"https://openalex.org/keywords/limited-training-data","display_name":"limited training data","score":0.7950000166893005}],"concepts":[{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.8739410638809204},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8344528675079346},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7675467729568481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6684821844100952},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5989350080490112},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5578652620315552},{"id":"https://openalex.org/C2778220771","wikidata":"https://www.wikidata.org/wiki/Q1522579","display_name":"Substitution (logic)","level":2,"score":0.5478229522705078},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5235564112663269},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5180113911628723},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5123463869094849},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4665958881378174},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4012904465198517},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34525078535079956},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1022636890411377},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2022.bionlp-1.6","doi":"https://doi.org/10.18653/v1/2022.bionlp-1.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.bionlp-1.6","pdf_url":"https://aclanthology.org/2022.bionlp-1.6.pdf","source":{"id":"https://openalex.org/S7407086806","display_name":"Workshop on Biomedical Language Processing (BioNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 21st Workshop on Biomedical Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2204.04711","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.04711","pdf_url":"https://arxiv.org/pdf/2204.04711","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2204.04711","doi":"https://doi.org/10.48550/arxiv.2204.04711","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2204.04711","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.bionlp-1.6","doi":"https://doi.org/10.18653/v1/2022.bionlp-1.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.bionlp-1.6","pdf_url":"https://aclanthology.org/2022.bionlp-1.6.pdf","source":{"id":"https://openalex.org/S7407086806","display_name":"Workshop on Biomedical Language Processing (BioNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 21st Workshop on Biomedical Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285214521.pdf","grobid_xml":"https://content.openalex.org/works/W4285214521.grobid-xml"},"referenced_works_count":81,"referenced_works":["https://openalex.org/W1532325895","https://openalex.org/W1614298861","https://openalex.org/W1981208470","https://openalex.org/W2126209950","https://openalex.org/W2148143831","https://openalex.org/W2251658415","https://openalex.org/W2251818205","https://openalex.org/W2528904340","https://openalex.org/W2594477595","https://openalex.org/W2606964149","https://openalex.org/W2612431505","https://openalex.org/W2767899794","https://openalex.org/W2796176247","https://openalex.org/W2799007037","https://openalex.org/W2805973097","https://openalex.org/W2888296173","https://openalex.org/W2891420675","https://openalex.org/W2898355739","https://openalex.org/W2898905149","https://openalex.org/W2905266130","https://openalex.org/W2911489562","https://openalex.org/W2912924812","https://openalex.org/W2917156138","https://openalex.org/W2938205538","https://openalex.org/W2949849869","https://openalex.org/W2951534261","https://openalex.org/W2954116343","https://openalex.org/W2954996726","https://openalex.org/W2962985038","https://openalex.org/W2963216553","https://openalex.org/W2963323070","https://openalex.org/W2963341956","https://openalex.org/W2963545917","https://openalex.org/W2963748441","https://openalex.org/W2964053384","https://openalex.org/W2965373594","https://openalex.org/W2970482702","https://openalex.org/W2970771982","https://openalex.org/W2970796366","https://openalex.org/W2971296908","https://openalex.org/W2975059944","https://openalex.org/W2978017171","https://openalex.org/W2979928633","https://openalex.org/W2980175352","https://openalex.org/W2986532682","https://openalex.org/W2988673764","https://openalex.org/W2998259147","https://openalex.org/W3004437239","https://openalex.org/W3005193031","https://openalex.org/W3012064577","https://openalex.org/W3013838212","https://openalex.org/W3022039293","https://openalex.org/W3035282664","https://openalex.org/W3035577668","https://openalex.org/W3035621030","https://openalex.org/W3037869352","https://openalex.org/W3045295485","https://openalex.org/W3047636089","https://openalex.org/W3089094490","https://openalex.org/W3089659770","https://openalex.org/W3090260555","https://openalex.org/W3092129462","https://openalex.org/W3100452049","https://openalex.org/W3103291112","https://openalex.org/W3105522431","https://openalex.org/W3105956114","https://openalex.org/W3106031848","https://openalex.org/W3115462295","https://openalex.org/W3117737817","https://openalex.org/W3120948048","https://openalex.org/W3122890974","https://openalex.org/W3135225500","https://openalex.org/W3152268000","https://openalex.org/W3154297739","https://openalex.org/W3162734203","https://openalex.org/W3170002521","https://openalex.org/W3176265725","https://openalex.org/W3176923149","https://openalex.org/W3180181113","https://openalex.org/W3197470290","https://openalex.org/W3212743961"],"related_works":["https://openalex.org/W4385376509","https://openalex.org/W4225154151","https://openalex.org/W4205765952","https://openalex.org/W2626667877","https://openalex.org/W3005193031","https://openalex.org/W4401042457","https://openalex.org/W3197462644","https://openalex.org/W3013838212","https://openalex.org/W4406711870","https://openalex.org/W3095609828"],"abstract_inverted_index":{"We":[0],"study":[1],"the":[2,16,30,67,102],"effect":[3],"of":[4,94,101],"seven":[5],"data":[6,28],"augmentation":[7],"(da)":[8],"methods":[9],"in":[10],"factoid":[11],"question":[12,63],"answering,":[13],"focusing":[14],"on":[15,56],"biomedical":[17,43],"domain,":[18],"where":[19],"obtaining":[20],"training":[21,37,117],"instances":[22,38,118],"is":[23,112],"particularly":[24],"difficult.We":[25],"experiment":[26],"with":[27,36,70],"from":[29,40],"bioasq":[31],"challenge,":[32],"which":[33],"we":[34],"augment":[35],"obtained":[39],"an":[41],"artificial":[42,116],"machine":[44],"reading":[45],"comprehension":[46],"dataset,":[47],"or":[48,59,65],"via":[49],"back-translation,":[50],"information":[51],"retrieval,":[52],"word":[53,107],"substitution":[54],"based":[55],"word2vec":[57],"embeddings":[58],"masked":[60],"language":[61],"modeling,":[62],"generation,":[64],"extending":[66],"given":[68],"passage":[69],"additional":[71],"context.We":[72],"show":[73],"that":[74],"da":[75,96,104],"can":[76],"lead":[77],"to":[78,90],"very":[79],"significant":[80],"performance":[81],"gains,":[82],"even":[83],"when":[84],"using":[85],"large":[86,98],"pretrained":[87,99],"Transformers,":[88],"contributing":[89],"a":[91],"broader":[92],"discussion":[93],"if/when":[95],"benefits":[97],"models.One":[100],"simplest":[103],"methods,":[105],"word2vec-based":[106],"substitution,":[108],"performed":[109],"best":[110],"and":[111,119],"recommended.We":[113],"release":[114],"our":[115],"code.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2022-07-14T00:00:00"}