{"id":"https://openalex.org/W4285223746","doi":"https://doi.org/10.18653/v1/2022.bionlp-1.20","title":"Few-Shot Cross-lingual Transfer for Coarse-grained De-identification of Code-Mixed Clinical Texts","display_name":"Few-Shot Cross-lingual Transfer for Coarse-grained De-identification of Code-Mixed Clinical Texts","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285223746","doi":"https://doi.org/10.18653/v1/2022.bionlp-1.20"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.bionlp-1.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.bionlp-1.20","pdf_url":"https://aclanthology.org/2022.bionlp-1.20.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 21st Workshop on Biomedical Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2022.bionlp-1.20.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036768397","display_name":"Saadullah Amin","orcid":"https://orcid.org/0000-0002-9915-5795"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Saadullah Amin","raw_affiliation_strings":["DFKI, SIC, Germany","Department of LST, Saarland University, Germany"],"affiliations":[{"raw_affiliation_string":"DFKI, SIC, Germany","institution_ids":[]},{"raw_affiliation_string":"Department of LST, Saarland University, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020046851","display_name":"Noon Pokaratsiri Goldstein","orcid":null},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Noon Pokaratsiri Goldstein","raw_affiliation_strings":["DFKI, SIC, Germany","Department of LST, Saarland University, Germany"],"affiliations":[{"raw_affiliation_string":"DFKI, SIC, Germany","institution_ids":[]},{"raw_affiliation_string":"Department of LST, Saarland University, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023041486","display_name":"Morgan Wixted","orcid":null},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Morgan Wixted","raw_affiliation_strings":["DFKI, SIC, Germany","Department of LST, Saarland University, Germany"],"affiliations":[{"raw_affiliation_string":"DFKI, SIC, Germany","institution_ids":[]},{"raw_affiliation_string":"Department of LST, Saarland University, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046498687","display_name":"Alejandro Garc\u00eda\u2010Rudolph","orcid":"https://orcid.org/0000-0003-0853-8334"},"institutions":[{"id":"https://openalex.org/I4210113915","display_name":"Institut Guttmann","ror":"https://ror.org/01xcgd076","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I4210113915"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alejandro Garcia-Rudolph","raw_affiliation_strings":["Department of Research and Innovation, Institut Guttmann, UAB, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Research and Innovation, Institut Guttmann, UAB, Spain","institution_ids":["https://openalex.org/I4210113915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031678501","display_name":"Catalina Mart\u00ednez-Costa","orcid":"https://orcid.org/0000-0003-1857-1744"},"institutions":[{"id":"https://openalex.org/I80180929","display_name":"Universidad de Murcia","ror":"https://ror.org/03p3aeb86","country_code":"ES","type":"education","lineage":["https://openalex.org/I80180929"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Catalina Mart\u00ednez-Costa","raw_affiliation_strings":["Department Inform\u00e1tica y Sistemas, Universidad de Murcia, IMIB-Arrixaca, Spain"],"affiliations":[{"raw_affiliation_string":"Department Inform\u00e1tica y Sistemas, Universidad de Murcia, IMIB-Arrixaca, Spain","institution_ids":["https://openalex.org/I80180929"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070147451","display_name":"Guenter Neumann","orcid":null},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Guenter Neumann","raw_affiliation_strings":["DFKI, SIC, Germany","Department of LST, Saarland University, Germany"],"affiliations":[{"raw_affiliation_string":"DFKI, SIC, Germany","institution_ids":[]},{"raw_affiliation_string":"Department of LST, Saarland University, Germany","institution_ids":["https://openalex.org/I91712215"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5036768397"],"corresponding_institution_ids":["https://openalex.org/I91712215"],"apc_list":null,"apc_paid":null,"fwci":0.3977,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66154879,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"200","last_page":"211"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9983000159263611,"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":0.986299991607666,"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":0.824884831905365},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.6648712158203125},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6366853713989258},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5959029793739319},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5493948459625244},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.5165513753890991},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5121397972106934},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49425601959228516},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4831089973449707},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.4827556014060974},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4783187210559845},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.367554247379303}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.824884831905365},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.6648712158203125},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6366853713989258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5959029793739319},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5493948459625244},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.5165513753890991},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5121397972106934},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49425601959228516},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4831089973449707},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.4827556014060974},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4783187210559845},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.367554247379303},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/v1/2022.bionlp-1.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.bionlp-1.20","pdf_url":"https://aclanthology.org/2022.bionlp-1.20.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 21st Workshop on Biomedical Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.bionlp-1.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.bionlp-1.20","pdf_url":"https://aclanthology.org/2022.bionlp-1.20.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 21st Workshop on Biomedical Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285223746.pdf","grobid_xml":"https://content.openalex.org/works/W4285223746.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W68059783","https://openalex.org/W128054572","https://openalex.org/W2015620729","https://openalex.org/W2053154970","https://openalex.org/W2101135401","https://openalex.org/W2190333735","https://openalex.org/W2296283641","https://openalex.org/W2396881363","https://openalex.org/W2509827822","https://openalex.org/W2621075239","https://openalex.org/W2624380710","https://openalex.org/W2625625371","https://openalex.org/W2798778171","https://openalex.org/W2941857399","https://openalex.org/W2952087486","https://openalex.org/W2952460928","https://openalex.org/W2952638691","https://openalex.org/W2963341956","https://openalex.org/W2963956191","https://openalex.org/W2970511757","https://openalex.org/W2970854433","https://openalex.org/W2971105085","https://openalex.org/W2990085462","https://openalex.org/W2997124358","https://openalex.org/W2997636389","https://openalex.org/W3010607409","https://openalex.org/W3021663125","https://openalex.org/W3101516616","https://openalex.org/W3105470358","https://openalex.org/W3117587092","https://openalex.org/W3153462499","https://openalex.org/W3175115403","https://openalex.org/W3175518369","https://openalex.org/W3176119108","https://openalex.org/W3177470889","https://openalex.org/W4288093580","https://openalex.org/W4289388781","https://openalex.org/W4376861636"],"related_works":["https://openalex.org/W3149011051","https://openalex.org/W3180764077","https://openalex.org/W4281560212","https://openalex.org/W3116252395","https://openalex.org/W2791025012","https://openalex.org/W2769084352","https://openalex.org/W4386322467","https://openalex.org/W4385574021","https://openalex.org/W2887593177","https://openalex.org/W2757016069"],"abstract_inverted_index":{"Despite":[0],"the":[1,13,89,118,146,154,170],"advances":[2],"in":[3,18,50,58,65,80,117],"digital":[4],"healthcare":[5],"systems":[6],"offering":[7],"curated":[8],"structured":[9],"knowledge,":[10],"much":[11],"of":[12,21,94,111,177],"critical":[14],"information":[15,34,39],"still":[16],"lies":[17],"large":[19],"volumes":[20],"unlabeled":[22],"and":[23,101,108],"unstructured":[24],"clinical":[25,114],"texts.":[26],"These":[27],"texts,":[28],"which":[29,60],"often":[30,61],"contain":[31],"protected":[32],"health":[33],"(PHI),":[35],"are":[36,62],"exposed":[37],"to":[38,104,127,151,165],"extraction":[40],"tools":[41],"for":[42,77,96,141],"downstream":[43],"applications,":[44],"risking":[45],"patient":[46],"identification.":[47],"Existing":[48],"works":[49],"de-identification":[51,116],"rely":[52],"on":[53,153],"using":[54],"large-scale":[55],"annotated":[56],"corpora":[57],"English,":[59],"not":[63],"suitable":[64],"realworld":[66],"multilingual":[67],"settings.":[68,82],"Pre-trained":[69],"language":[70],"models":[71],"(LM)":[72],"have":[73],"shown":[74],"great":[75],"potential":[76],"cross-lingual":[78,91],"transfer":[79,92],"low-resource":[81,107],"In":[83],"this":[84],"work,":[85],"we":[86,133],"empirically":[87],"show":[88],"few-shot":[90,129],"property":[93],"LMs":[95],"named":[97],"entity":[98],"recognition":[99],"(NER)":[100],"apply":[102],"it":[103],"solve":[105],"a":[106,123,136,174],"real-world":[109],"challenge":[110],"code-mixed":[112],"(Spanish-Catalan)":[113],"notes":[115],"stroke":[119],"domain.":[120],"We":[121],"annotate":[122],"gold":[124,155],"evaluation":[125,156],"dataset":[126],"assess":[128],"setting":[130],"performance":[131],"where":[132],"only":[134],"use":[135],"few":[137],"hundred":[138],"labeled":[139],"examples":[140],"training.":[142],"Our":[143],"model":[144,172],"improves":[145],"zero-shot":[147],"F1-score":[148,176],"from":[149],"73.7%":[150],"91.2%":[152],"set":[157],"when":[158],"adapting":[159],"Multilingual":[160],"BERT":[161],"(mBERT)":[162],"When":[163],"generalized":[164],"an":[166],"out-of-sample":[167],"test":[168],"set,":[169],"best":[171],"achieves":[173],"humanevaluation":[175],"97.2%.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}