FRE @ BC8 SympTEMIST track: Named Entity Recognition

Abstract

This paper describes our submission on the SympTEMIST Named Entity Recognition (NER) shared subtask at BioCreative 2023. We submitted two systems based on a RoBERTa architecture LLM trained on Spanish-language clinical data available at HuggingFace model repository. The techniques that we used for both systems are Conditional Random Fields (CRF) and Byte-Pair Encoding dropout (BPE dropout). In the second system we also included Sub-subword feature based embeddings (SSW). Our systems obtained strict F1-score 0.727 and 0.728 with and without SSW, respectively.

This article is part of the Proceedings of the BioCreative VIII Challenge and Workshop: Curation and Evaluation in the era of Generative Models.