Une expérience de sémantique inférentielle
Farid Nouioua, Daniel Kayser
Abstract
We develop a system which must be able to perform the same inferences that a human reader of an accident report can do and more particularly to determine the apparent causes of the accident. We describe the general framework in which we are situated, linguistic and semantic levels of the analysis and the inference rules used by the system.
Create a lesson
Related papers
Towards a Belief-Based World Model for LLM Agents
Shubham Kumar, Harshit Kumar, Narendra Ahuja et al.
mimeo: Compiling Public Expert Corpora into Agent Skills and Testing What Transfers
Timothy Kassis
Conversation Coach: A Voice-enabled AI System that Helps Practice Difficult Workplace Conversations
Fanyou Wu, Suraj Maharjan, Ainur Yessenalina et al.
SAGE: State-Grounded, Abstention-Aware Evaluation of Task-Oriented Dialogue Agents
Rayan Khoury, Shih-Yao Lin, Pratyush Mishra
SpecMind: Enabling Spectrum Intelligence via Multi-Agent Hybrid Retrieval-Augmented Generation
Songwei Dong, Bingyan Lu, Makayla Kienlen et al.
RestoreBench: Can AI Agents Restore Power Flow Convergence?
Riccardo Mansutti, Andrea Pomarico, Robert Jakob et al.