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 developped 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.

This paper introduces DACCORD, an original dataset in French for automatic detection of contradictions between sentences. It also presents new, manually translated versions of two datasets, namely the well known dataset RTE3 and the recent dataset GQNLI, from English to French, for the task of natural language inference / recognising textual entailment, which is a sentence-pair classification task. These datasets help increase the admittedly limited number of datasets in French available for these tasks. DACCORD consists of 1034 pairs of sentences and is the first dataset exclusively dedicated to this task and covering among others the topic of the Russian invasion in Ukraine. RTE3-FR contains 800 examples for each of its validation and test subsets, while GQNLI-FR is composed of 300 pairs of sentences and focuses specifically on the use of generalised quantifiers. Our experiments on these datasets show that they are more challenging than the two already existing datasets for the mainstream NLI task in French (XNLI, FraCaS). For languages other than English, most deep learning models for NLI tasks currently have only XNLI available as a training set. Additional datasets, such as ours for French, could permit different training and evaluation strategies, producing more robust results and reducing the inevitable biases present in any single dataset.

Ce travail s’inscrit dans l’analyse automatique d’un corpus de récits de voyage. À cette fin, nous raffinons la sémantique de Montague pour rendre compte des phénomènes d’adaptation du sens des mots au contexte dans lequel ils apparaissent. Ici, nous modélisons les constructions de type ‘le chemin descend pendant une demi-heure’ où ledit chemin introduit un voyageur fictif qui le parcourt, en étendant des idées que le dernier auteur a développé avec Bassac et Mery. Cette introduction du voyageur utilise la montée de type afin que le quantificateur introduisant le voyageur porte sur toute la phrase et que les propriétés du chemin ne deviennent pas des propriétés du voyageur, fût-il fictif. Cette analyse sémantique (ou plutôt sa traduction en lambda-DRT) est d’ores et déjà implantée pour une partie du lexique de Grail.