Large language models (LLMs) have demonstrated remarkable capabilities across diverse domains, yet their adaptation to specialized fields remains challenging, particularly for non-English languages. This study investigates domain-adaptive pre-training (DAPT) as a strategy for specializing small to mid-sized LLMs in the French biomedical domain through continued pre-training. We address two key research questions: the viability of specialized continued pre-training for domain adaptation and the relationship between domain-specific performance gains and general capability degradation. Our contributions include the release of a fully open-licensed French biomedical corpus suitable for commercial and open-source applications, the training and release of specialized French biomedical LLMs, and novel insights for DAPT implementation. Our methodology encompasses the collection and refinement of high-quality French biomedical texts, the exploration of causal language modeling approaches using DAPT, and conducting extensive comparative evaluations. Our results cast doubt on the efficacy of DAPT, in contrast to previous works, but we highlight its viability in smaller-scale, resource-constrained scenarios under the right conditions. Our findings further suggest that model merging post-DAPT is essential to mitigate generalization trade-offs, and in some cases even improves performance on specialized tasks at which the DAPT was directed.

We release Pantagruel models, a new family of self-supervised encoder models for French text and speech. Instead of predicting modality-tailored targets such as textual tokens or speech units, Pantagruel learns contextualized target representations in the feature space, allowing modality-specific encoders to capture linguistic and acoustic regularities more effectively. Separate models are pre-trained on large-scale French corpora, including Wikipedia, OSCAR and CroissantLLM for text, together with MultilingualLibriSpeech, LeBenchmark, and INA-100k for speech. INA-100k is a newly introduced 100,000-hour corpus of French audio derived from the archives of the Institut National de l’Audiovisuel (INA), the national repository of French radio and television broadcasts, providing highly diverse audio data. We evaluate Pantagruel across a broad range of downstream tasks spanning both modalities, including those from the standard French benchmarks such as FLUE or LeBenchmark. Across these tasks, Pantagruel models show competitive or superior performance compared to strong French baselines such as CamemBERT, FlauBERT, and LeBenchmark2.0, while maintaining a shared architecture that can seamlessly handle either speech or text inputs. These results confirm the effectiveness of feature-space self-supervised objectives for French representation learning and highlight Pantagruel as a robust foundation for multimodal speech-text understanding.

This article presents MedDialog-FR, a large publicly available corpus of French medical conversations for the medical domain. Motivated by the lack of French dialogue corpora for data-driven dialogue systems and the paucity of available information related to women’s intimate health, we introduce an annotated corpus of question-and-answer dialogues between a real patient and a real doctor concerning women’s intimate health. The corpus is composed of about 20,000 dialogues automatically translated from the English version of MedDialog-EN. The corpus test set is composed of 1,400 dialogues that have been manually post-edited and annotated with 22 categories from the UMLS ontology. We also fine-tuned state-of-the-art reference models to automatically perform multi-label classification and response generation to give an initial performance benchmark and highlight the difficulty of the tasks.

Pretrained Language Models (PLMs) are the de facto backbone of most state-of-the-art NLP systems. In this paper, we introduce a family of domain-specific pretrained PLMs for French, focusing on three important domains: transcribed speech, medicine, and law. We use a transformer architecture based on efficient methods (LinFormer) to maximise their utility, since these domains often involve processing long documents. We evaluate and compare our models to state-of-the-art models on a diverse set of tasks and datasets, some of which are introduced in this paper. We gather the datasets into a new French-language evaluation benchmark for these three domains. We also compare various training configurations: continued pretraining, pretraining from scratch, as well as single- and multi-domain pretraining. Extensive domain-specific experiments show that it is possible to attain competitive downstream performance even when pre-training with the approximative LinFormer attention mechanism. For full reproducibility, we release the models and pretraining data, as well as contributed datasets.

Les modèles de langue préentraînés (PLM) constituent aujourd’hui de facto l’épine dorsale de la plupart des systèmes de traitement automatique des langues. Dans cet article, nous présentons Jargon, une famille de PLMs pour des domaines spécialisés du français, en nous focalisant sur trois domaines : la parole transcrite, le domaine clinique / biomédical, et le domaine juridique. Nous utilisons une architecture de transformeur basée sur des méthodes computationnellement efficaces(LinFormer) puisque ces domaines impliquent souvent le traitement de longs documents. Nous évaluons et comparons nos modèles à des modèles de l’état de l’art sur un ensemble varié de tâches et de corpus d’évaluation, dont certains sont introduits dans notre article. Nous rassemblons les jeux de données dans un nouveau référentiel d’évaluation en langue française pour ces trois domaines. Nous comparons également diverses configurations d’entraînement : préentraînement prolongé en apprentissage autosupervisé sur les données spécialisées, préentraînement à partir de zéro, ainsi que préentraînement mono et multi-domaines. Nos expérimentations approfondies dans des domaines spécialisés montrent qu’il est possible d’atteindre des performances compétitives en aval, même lors d’un préentraînement avec le mécanisme d’attention approximatif de LinFormer. Pour une reproductibilité totale, nous publions les modèles et les données de préentraînement, ainsi que les corpus utilisés.

Pre-trained transformer language models (LMs) have in recent years become the dominant paradigm in applied NLP. These models have achieved state-of-the-art performance on tasks such as information extraction, question answering, sentiment analysis, document classification and many others. In the biomedical domain, significant progress has been made in adapting this paradigm to NLP tasks that require the integration of domain-specific knowledge as well as statistical modelling of language. In particular, research in this area has focused on the question of how best to construct LMs that take into account not only the patterns of token distribution in medical text, but also the wealth of structured information contained in terminology resources such as the UMLS. This work contributes a data-centric paradigm for enriching the language representations of biomedical transformer-encoder LMs by extracting text sequences from the UMLS.This allows for graph-based learning objectives to be combined with masked-language pre-training. Preliminary results from experiments in the extension of pre-trained LMs as well as training from scratch show that this framework improves downstream performance on multiple biomedical and clinical Named Entity Recognition (NER) tasks. All pre-trained models, data processing pipelines and evaluation scripts will be made publicly available.

Des travaux récents dans le domaine du traitement du langage naturel ont démontré l’efficacité des modèles de langage pré-entraînés pour une grande variété d’applications générales. Les modèles de langage à grande échelle acquièrent généralement ces capacités en modélisant la distribution statistique des mots par un apprentissage auto-supervisé sur de grandes quantités de texte. Toutefois, pour les domaines spécialisés à faibles ressources, tels que le traitement de documents cliniques, en particulier dans des langues autres que l’anglais, la nécessité d’intégrer des connaissances structurées reste d’une grande importance. Cet article se concentre sur l’une de ces applications spécialisées de la modélisation du langage à partir de ressources limitées : l’extraction d’informations à partir de documents biomédicaux et cliniques en français. En particulier, nous montrons qu’en complétant le pré-entraînement en mots masqués des réseaux neuronaux transformer par des objectifs de prédiction extraits d’une base de connaissances biomédicales, leurs performances sur deux tâches différentes de reconnaissance d’entités nommées en français peuvent être augmentées.

Cet article présente un résumé de notre soumission pour Tâche 1 de DEFT 2021. Cette tâche consiste à identifier le profil clinique d’un patient à partir d’une description textuelle de son cas clinique en identifiant les types de pathologie mentionnés dans le texte. Ce travail étudie des approches de classification de texte utilisant des plongements de mots contextualisés en français. À partir d’une base de référence d’un modèle constitué pour la compréhension générale de la langue française, nous utilisons des modèles pré-entraînés avec masked language modelling et affinés à la tâche d’identification, en utilisant un corpus externe de textes cliniques fourni par SOS Médecins, pour développer des ensembles de classifieurs binaires associant les textes cliniques à des catégories de pathologies.