@inproceedings{skandalis-etal-2025-neurosymbolic,
    title = "Neurosymbolic {AI} for Natural Language Inference in {F}rench : combining {LLM}s and theorem provers for semantic parsing and natural language reasoning",
    author = "Skandalis, Maximos  and
      Abzianidze, Lasha  and
      Moot, Richard  and
      Retor{\'e}, Christian  and
      Robillard, Simon",
    editor = "Evang, Kilian  and
      Kallmeyer, Laura  and
      Pogodalla, Sylvain",
    booktitle = "Proceedings of the 16th International Conference on Computational Semantics",
    month = sep,
    year = "2025",
    address = {D{\"u}sseldorf, Germany},
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/2025.iwcs-1.22/",
    pages = "252--263",
    ISBN = "979-8-89176-316-6",
    abstract = "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."
}