The biomedical domain has sparked a significant interest in the field of Natural Language Processing (NLP), which has seen substantial advancements with pre-trained language models (PLMs). However, comparing these models has proven challenging due to variations in evaluation protocols across different models. A fair solution is to aggregate diverse downstream tasks into a benchmark, allowing for the assessment of intrinsic PLMs qualities from various perspectives. Although still limited to few languages, this initiative has been undertaken in the biomedical field, notably English and Chinese. This limitation hampers the evaluation of the latest French biomedical models, as they are either assessed on a minimal number of tasks with non-standardized protocols or evaluated using general downstream tasks. To bridge this research gap and account for the unique sensitivities of French, we present the first-ever publicly available French biomedical language understanding benchmark called DrBenchmark. It encompasses 20 diversified tasks, including named-entity recognition, part-of-speech tagging, question-answering, semantic textual similarity, or classification. We evaluate 8 state-of-the-art pre-trained masked language models (MLMs) on general and biomedical-specific data, as well as English specific MLMs to assess their cross-lingual capabilities. Our experiments reveal that no single model excels across all tasks, while generalist models are sometimes still competitive.

We present a manually annotated new corpus, Species-Species Interaction (SSI), for extracting meaningful binary relations between species, in biomedical texts, at sentence level, with a focus on the gut microbiota. The corpus leverages PubTator to annotate species in full-text articles after evaluating different NER species taggers. Our first results are promising for extracting relations between species using BERT and its biomedical variants.

Nous nous intéressons à l’extraction de relations, dans des articles scientifiques, portant sur le microbiome humain. Afin de construire un corpus annoté, nous avons évalué l’utilisation de l’ontologie OHMI pour détecter les relations présentes dans les phrases des articles scientifiques, en calculant la similarité sémantique entre les relations définies dans l’ontologie et les phrases des articles. Le modèle BERT et trois variantes biomédicales sont utilisés pour obtenir les représentations des relations et des phrases. Ces modèles sont comparés sur un corpus construit à partir d’articles scientifiques complets issus de la plateforme ISTEX, dont une sous-partie a été annotée manuellement.