Neural Proof Nets - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier
Conference Papers Year : 2020

Neural Proof Nets

Abstract

Linear logic and the linear {\lambda}-calculus have a long standing tradition in the study of natural language form and meaning. Among the proof calculi of linear logic, proof nets are of particular interest, offering an attractive geometric representation of derivations that is unburdened by the bureaucratic complications of conventional prooftheoretic formats. Building on recent advances in set-theoretic learning, we propose a neural variant of proof nets based on Sinkhorn networks, which allows us to translate parsing as the problem of extracting syntactic primitives and permuting them into alignment. Our methodology induces a batch-efficient, end-to-end differentiable architecture that actualizes a formally grounded yet highly efficient neuro-symbolic parser. We test our approach on {\AE}Thel, a dataset of type-logical derivations for written Dutch, where it manages to correctly transcribe raw text sentences into proofs and terms of the linear {\lambda}-calculus with an accuracy of as high as 70%.
Fichier principal
Vignette du fichier
2009.12702.pdf (639.84 Ko) Télécharger le fichier
Loading...

Dates and versions

lirmm-02952267 , version 1 (29-09-2020)

Licence

Identifiers

Cite

Konstantinos Kogkalidis, Michael Moortgat, Richard Moot. Neural Proof Nets. CoNLL 2020 - 24th Conference on Computational Natural Language Learning, Nov 2020, Virtual, Dominican Republic. pp.26-40, ⟨10.18653/v1/2020.conll-1.3⟩. ⟨lirmm-02952267⟩
90 View
52 Download

Altmetric

Share

More