{"id":"https://openalex.org/W7028069805","doi":null,"title":"Entity Recognition and Linking for Biomedical Documents Applying recent Transformer-based Entity Recognition and Linking Algorithms for the Biomedical Domain, to a Multi-Lingual Scenario","display_name":"Entity Recognition and Linking for Biomedical Documents Applying recent Transformer-based Entity Recognition and Linking Algorithms for the Biomedical Domain, to a Multi-Lingual Scenario","publication_year":2024,"publication_date":"2024-11-01","ids":{"openalex":"https://openalex.org/W7028069805"},"language":"en","primary_location":{"id":"pmh:oai:run.unl.pt:10362/182370","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10362/182370","pdf_url":"https://run.unl.pt/bitstreams/10f612d4-7269-47fd-9fb0-5f32955d4c58/download","source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"master thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://run.unl.pt/bitstreams/10f612d4-7269-47fd-9fb0-5f32955d4c58/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Gon\u00e7alves, Rodrigo Miguel Gameiro Vilhena","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gon\u00e7alves, Rodrigo Miguel Gameiro Vilhena","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9854000210762024,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9854000210762024,"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/T10028","display_name":"Topic Modeling","score":0.01360000018030405,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.00019999999494757503,"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/named-entity-recognition","display_name":"named entity recognition","score":0.9319999814033508},{"id":"https://openalex.org/keywords/entity-linking","display_name":"entity linking","score":0.9959999918937683},{"id":"https://openalex.org/keywords/biomedical-text","display_name":"biomedical text","score":0.5680000185966492},{"id":"https://openalex.org/keywords/multilingual-nlp","display_name":"multilingual NLP","score":0.8820000290870667},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.8939999938011169},{"id":"https://openalex.org/keywords/pre-trained-transformers","display_name":"pre-trained transformer models","score":0.7639999985694885},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.9629999995231628},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.7440000176429749},{"id":"https://openalex.org/keywords/information-extraction","display_name":"information extraction","score":0.7210000157356262}],"concepts":[{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.878600001335144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.842199981212616},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6626999974250793},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6148999929428101},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5759000182151794},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5649999976158142},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5649999976158142},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.39660000801086426},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.375900000333786},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3662000000476837},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.3610000014305115},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.35760000348091125},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.3522999882698059},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3395000100135803},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3084000051021576},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.262800008058548}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:run.unl.pt:10362/182370","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10362/182370","pdf_url":"https://run.unl.pt/bitstreams/10f612d4-7269-47fd-9fb0-5f32955d4c58/download","source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"master thesis"}],"best_oa_location":{"id":"pmh:oai:run.unl.pt:10362/182370","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10362/182370","pdf_url":"https://run.unl.pt/bitstreams/10f612d4-7269-47fd-9fb0-5f32955d4c58/download","source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"master thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7028069805.pdf","grobid_xml":"https://content.openalex.org/works/W7028069805.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1614298861","https://openalex.org/W1623072288","https://openalex.org/W1940872118","https://openalex.org/W1981797826","https://openalex.org/W2013720308","https://openalex.org/W2064675550","https://openalex.org/W2070808142","https://openalex.org/W2107890417","https://openalex.org/W2112796928","https://openalex.org/W2114361266","https://openalex.org/W2133564696","https://openalex.org/W2149706766","https://openalex.org/W2159583324","https://openalex.org/W2493916176","https://openalex.org/W2585785990","https://openalex.org/W2626778328","https://openalex.org/W2788784374","https://openalex.org/W2896457183","https://openalex.org/W2925863688","https://openalex.org/W2982399380","https://openalex.org/W2983040767","https://openalex.org/W2986154550","https://openalex.org/W3046375318","https://openalex.org/W3087801495","https://openalex.org/W3101058639","https://openalex.org/W3104748221","https://openalex.org/W3136657289","https://openalex.org/W3153986565","https://openalex.org/W3164540570","https://openalex.org/W3169066049","https://openalex.org/W3171351722","https://openalex.org/W3175655865","https://openalex.org/W3199006805","https://openalex.org/W4200136492","https://openalex.org/W4221153690","https://openalex.org/W4223492536","https://openalex.org/W4224308101","https://openalex.org/W4285197708","https://openalex.org/W4285214521","https://openalex.org/W4295807725","https://openalex.org/W4308760226","https://openalex.org/W4362598818","https://openalex.org/W4381662634","https://openalex.org/W4382404920","https://openalex.org/W4385565282","https://openalex.org/W4391494850","https://openalex.org/W4392935324","https://openalex.org/W4401042659","https://openalex.org/W4405867157","https://openalex.org/W4406152279","https://openalex.org/W6911304643","https://openalex.org/W6948729738","https://openalex.org/W6967751204","https://openalex.org/W7131792799"],"related_works":["https://openalex.org/W4381662634","https://openalex.org/W7126122784","https://openalex.org/W7081627544","https://openalex.org/W4296886375","https://openalex.org/W3015281440","https://openalex.org/W4396789721","https://openalex.org/W4200381505","https://openalex.org/W4395082718","https://openalex.org/W7202212755","https://openalex.org/W4313526646"],"abstract_inverted_index":{"In":[0],"the":[1,22,31,52,90,97,114,133,139,151,166,173,183,204,221],"ever":[2],"expanding":[3],"domain":[4,83,206],"of":[5,9,18,25,33,54,99,141,153,175],"Biomedicine,":[6],"a":[7,37,160,194,233],"wealth":[8],"crucial":[10],"information":[11],"is":[12],"embedded":[13],"within":[14,113,203],"an":[15,48],"extensive":[16],"number":[17],"free-text":[19],"documents.":[20],"However,":[21],"unstructured":[23],"nature":[24],"this":[26],"textual":[27],"reservoir,":[28],"coupled":[29],"with":[30],"intricacy":[32],"biomedical":[34,75,100,155,205],"terminology,":[35],"poses":[36],"significant":[38],"challenge":[39],"for":[40,92,196,207,214,226,237],"automated":[41],"systems":[42],"to":[43,58,150,164,171,248],"extract":[44],"valuable":[45,67],"insights":[46],"in":[47,73,240],"efficient":[49],"way.":[50],"Furthermore,":[51],"majority":[53],"resources":[55],"are":[56],"allocated":[57],"English,":[59],"but":[60],"other":[61,249],"lower-":[62],"resource":[63],"languages":[64,250],"also":[65],"contain":[66],"information.":[68],"The":[69],"current":[70],"state-of-the-art":[71,235],"models":[72,149],"multilingual":[74,154],"Natural":[76,109],"Language":[77,110],"Processing":[78,111],"lag":[79],"behind":[80],"their":[81],"general":[82],"and":[84,123,169,186,199,217,223,230,251],"English-specific":[85],"counterparts.":[86],"This":[87,104],"disparity":[88],"emphasizes":[89],"need":[91],"approaches":[93,181],"that":[94,192],"can":[95,244],"tackle":[96,128],"complexity":[98],"literature":[101],"across":[102],"languages.":[103,209],"dissertation":[105],"focuses":[106],"on":[107,182],"two":[108],"tasks":[112,189],"infor-":[115],"mation":[116],"extraction":[117],"realm:":[118],"Named":[119],"Entity":[120,124],"Recognition":[121],"(NER)":[122],"Linking":[125],"(EL).":[126],"To":[127],"these":[129],"tasks,":[130,229],"we":[131,137,158],"used":[132],"following":[134],"methodology:":[135],"first,":[136],"investigated":[138],"efficacy":[140],"transfer":[142],"learning":[143],"approaches,":[144],"by":[145],"adapting":[146],"pre-trained":[147],"Transformer-based":[148],"complexities":[152],"texts.":[156],"Second,":[157],"employed":[159],"data":[161,168],"augmentation":[162],"technique":[163],"enrich":[165],"training":[167],"try":[170],"enhance":[172],"performance":[174],"those":[176,227],"models.":[177],"We":[178,210],"evaluated":[179],"our":[180],"SympTEMIST,":[184],"CANTEMIST":[185],"MultiCardioNER":[187],"shared":[188,228],"-":[190],"competitions":[191],"provide":[193],"benchmark":[195],"evaluating":[197],"NER":[198,216],"EL":[200],"tech-":[201],"niques":[202],"various":[208],"obtained":[211],"competitive":[212],"results":[213,225],"both":[215],"EL,":[218],"consistently":[219],"surpassing":[220],"mean":[222],"median":[224],"even":[231],"establishing":[232],"new":[234],"score":[236],"DrugTEMIST":[238],"English":[239],"NER.":[241],"Our":[242],"methodology":[243],"be":[245],"easily":[246],"extended":[247],"datasets.":[252]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}