A RoBERTa NER model with BiLSTM-CRF and SapBERT candidate generation via cosine similarity was applied to symptom recognition and linking, where knowledge base selection most affected accuracy.
Learning domain- specialised representations for cross-lingual biomedical entity linking
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Team Fusion@ SU@ BC8 SympTEMIST track: transformer-based approach for symptom recognition and linking
A RoBERTa NER model with BiLSTM-CRF and SapBERT candidate generation via cosine similarity was applied to symptom recognition and linking, where knowledge base selection most affected accuracy.