Communication Dans Un Congrès Année : 2025

Neurosymbolic AI for Natural Language Inference in French : combining LLMs and theorem provers for semantic parsing and natural language reasoning

Résumé

In this article, we describe the first comprehensive neurosymbolic pipeline for the task of Natural Language Inference (NLI) for French, with the synergy of Large Language Models (CamemBERT) and automated theorem provers (GrailLight, LangPro). LLMs prepare the input for GrailLight by tagging each token with Part-of-Speech and grammatical information based on the Type-Logical Grammar formalism. GrailLight then produces the lambda-terms given as input to the LangPro theorem prover, a tableau-based theorem prover for natural logic originally developed for English. Currently, the proposed system works on the French version of SICK dataset. The results obtained are comparable to the ones on the English and Dutch versions of SICK with the same LangPro theorem prover, and are better than the results of recent transformers on this specific dataset. Finally, we have identified ways to further improve the results obtained, such as giving access to the theorem prover to lexical knowledge via a knowledge base for French.

Fichier principal
Vignette du fichier
IWCS_2025_paper.pdf (1.03 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
licence

Dates et versions

hal-05350875 , version 1 (06-11-2025)

Licence

Identifiants

  • HAL Id : hal-05350875 , version 1

Citer

Maximos Skandalis, Lasha Abzianidze, Richard Moot, Christian Retoré, Simon Robillard. Neurosymbolic AI for Natural Language Inference in French : combining LLMs and theorem provers for semantic parsing and natural language reasoning. IWCS 2025 - 16th International Conference on Computational Semantics, Heinrich Heine University (HHU) Düsseldorf; ACL Special Interest Group on Computational Semantics (SIGSEM), Sep 2025, Düsseldorf, Germany. pp.242-253. ⟨hal-05350875⟩
565 Consultations
211 Téléchargements

Partager

  • More