Groupe d’Étude en Traduction AutomatiqueTraitement Automatisé des Langues et de la Parole
Study Group for Machine Translation and Automated Processing of Languages and Speech
A multidisciplinary LIG team addressing the theoretical, methodological and practical aspects of multilingual communication and information processing, written or spoken.
Upcoming seminars
-
PhD defenseYagmur Ozturk (LIG (GETALP, SIGMA))Supporting post-publication peer review: Empirical investigations, computational methods and guidelines
-
Margot MassonTitle to be announced
News
- Nouveau site web de l'équipe
- Welcome to Chuyuan Li, CNRS researcher
- Welcome to Maxime Calka, associate professor
- bluesky 🚀 Deux postes de Maître·sse·s de Conférences ouverts – "IA et ses applications" (IUT-2) et …
- bluesky Congratulations to Yongxin Zhou for winning the Best Evaluation Award at INLG 2025 …
- bluesky Join 🏔️ ALPS 2026 for a week-long winter school in the French Alps at Aussois (1500m) from …
Recent publications
- Conference paper Vertical: Quality Estimation of Machine Translation from Université Grenoble Alpes
- Conference paper Retrieval-Augmented LLM Agents: Learning to Learn from Experience
- Conference paper Beyond Rhythm and Prosody: Inter-Utterance Silence Predicts Drone Movement Duration in Spontaneous Vocal Guidance
- Conference paper Observable Patterns Are Not Explanations: A Causal-Geometric Analysis of Latent Reasoning Models
- Conference paper Web Search Is Not Enough: LLMs Fail to Account for Paper Retraction Status
Research axes
Methods
Tasks and applications
Featured resources
DBnary
Multilingual lexical data extracted from Wiktionary, published as Linguistic Linked Open Data; new release twice a month.
FlauBERT
Unsupervised language model pre-training for French.
LeBenchmark
Reproducible benchmark for French speech SSL models on ASR, SLU, speech translation and emotion recognition.
PxCorpus
First spoken medical drug-prescription corpus in French (4 h, 55 speakers) for spoken language understanding and dialogue.
