A Benchmark Evaluation of Clinical Named Entity Recognition in French

arXiv:2403.19726v1 Announce Type: new
Abstract: Background: Transformer-based language models have shown strong performance on many Natural LanguageProcessing (NLP) tasks. Masked Language Models (MLMs) attract sustained interest because they can be adaptedto different languages and sub-domains through training or fine-tuning on specific corpora while remaining lighterthan modern Large Language Models (LLMs). Recently, several MLMs have been released for the biomedicaldomain in French, and experiments suggest that they outperform standard French counterparts. However, nosystematic evaluation comparing all models on the same corpora …

abstract arxiv benchmark clinical cs.ai cs.cl domains evaluation fine-tuning french language language models languages large language large language models llms modern natural nlp performance q-bio.qm recognition tasks through training transformer type