Perspectives on neural proof nets - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Perspectives on neural proof nets

Résumé

In this paper I will present a novel way of combining proof net proof search with neural networks. It contrasts with the ‘standard’ approach which has been applied to proof search in type-logical grammars in various different forms. In the standard approach, we first transform words to formulas (supertagging) then match atomic formulas to obtain a proof. I will introduce an alternative way to split the task into two: first, we generate the graph structure in a way which guarantees it corresponds to a lambda-term, then we obtain the detailed structure using vertex labelling. Vertex labelling is a well-studied task in graph neural networks, and different ways of implementing graph generation using neural networks will be explored.
Fichier principal
Vignette du fichier
perspectives.pdf (288.58 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

lirmm-03842908 , version 1 (07-11-2022)

Licence

Identifiants

Citer

Richard Moot. Perspectives on neural proof nets. EPTCS 2022 - End-to-End Compositional Models of Vector-Based Semantics, Aug 2022, Galway, Ireland. ⟨lirmm-03842908⟩
24 Consultations
22 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More