Team Fusion@ SU@ BC8 SympTEMIST track: transformer-based approach for symptom recognition and linking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Grazhdanski, Georgi, Vassileva, Sylvia, Koychev, Ivan, Boytcheva, Svetla
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913013373599744
author Grazhdanski, Georgi
Vassileva, Sylvia
Koychev, Ivan
Boytcheva, Svetla
author_facet Grazhdanski, Georgi
Vassileva, Sylvia
Koychev, Ivan
Boytcheva, Svetla
contents This paper presents a transformer-based approach to solving the SympTEMIST named entity recognition (NER) and entity linking (EL) tasks. For NER, we fine-tune a RoBERTa-based (1) token-level classifier with BiLSTM and CRF layers on an augmented train set. Entity linking is performed by generating candidates using the cross-lingual SapBERT XLMR-Large (2), and calculating cosine similarity against a knowledge base. The choice of knowledge base proves to have the highest impact on model accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2604_06424
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Team Fusion@ SU@ BC8 SympTEMIST track: transformer-based approach for symptom recognition and linking
Grazhdanski, Georgi
Vassileva, Sylvia
Koychev, Ivan
Boytcheva, Svetla
Computation and Language
Artificial Intelligence
This paper presents a transformer-based approach to solving the SympTEMIST named entity recognition (NER) and entity linking (EL) tasks. For NER, we fine-tune a RoBERTa-based (1) token-level classifier with BiLSTM and CRF layers on an augmented train set. Entity linking is performed by generating candidates using the cross-lingual SapBERT XLMR-Large (2), and calculating cosine similarity against a knowledge base. The choice of knowledge base proves to have the highest impact on model accuracy.
title Team Fusion@ SU@ BC8 SympTEMIST track: transformer-based approach for symptom recognition and linking
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2604.06424