neural-proof-nets
A neural parser for typelogical grammars based on Sinkhorn Networks and Proof Nets.
view repo
Linear logic and the linear λ-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 ÆThel, 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 λ-calculus with an accuracy of as high as 70
READ FULL TEXT
Since the very beginning of the theory of linear logic it is known how t...
read it
We present a framework for deriving inference relations between Dutch
se...
read it
In this paper, we show how to interpret a language featuring concurrency...
read it
We present a proof-theoretic analysis of the logic NLλ (Barker &
Shan 20...
read it
Abstract categorial grammars (ACG), as well as some other, closely relat...
read it
This document is intended to eventually gather a few small remarks on th...
read it
The short note describes the chart parser for multimodal type-logical
gr...
read it
A neural parser for typelogical grammars based on Sinkhorn Networks and Proof Nets.
Comments
There are no comments yet.