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.

La tâche de détection automatique de contradictions logiques entre énoncés en TALN est une tâche de classification binaire, où chaque paire de phrases reçoit une étiquette selon que les deux phrases se contredisent ou non. Elle peut être utilisée afin de lutter contre la désinformation. Dans cet article, nous présentons DACCORD, un jeu de données dédié à la tâche de détection automatique de contradictions entre phrases en français. Le jeu de données élaboré est actuellement composé de 1034 paires de phrases. Il couvre les thématiques de l’invasion de la Russie en Ukraine en 2022, de la pandémie de Covid-19 et de la crise climatique. Pour mettre en avant les possibilités de notre jeu de données, nous évaluons les performances de certains modèles de transformeurs sur lui. Nous constatons qu’il constitue pour eux un défi plus élevé que les jeux de données existants pour le français, qui sont déjà peu nombreux.In NLP, the automatic detection of logical contradictions between statements is a binary classification task, in which a pair of sentences receives a label according to whether or not the two sentences contradict each other. This task has many potential applications, including combating disinformation. In this article, we present DACCORD, a new dataset dedicated to the task of automatically detecting contradictions between sentences in French. The dataset is currently composed of 1034 sentence pairs. It covers the themes of Russia’s invasion of Ukraine in 2022, the Covid-19 pandemic, and the climate crisis. To highlight the possibilities of our dataset, we evaluate the performance of some recent Transformer models on it. We conclude that our dataset is considerably more challenging than the few existing datasets for French.