Perspectives on neural proof nets
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Graph GenerationSimilar Papers 제목 키워드 기반
Neural Proof Nets
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…
Spurious Ambiguity and Focalization
Spurious ambiguity is the phenomenon whereby distinct derivations in grammar may assign the same structural reading, resulting in redundancy in the parse search space and inefficiency in parsing. Understanding the proble…
Proof nets for the Displacement calculus
We present a proof net calculus for the Displacement calculus and show its correctness. This is the first proof net calculus which models the Displacement calculus directly and not by some sort of translation into anothe…
TranslationA Fully Rigorous Proof of the Derivation of Xavier and He's Initialization for Deep ReLU Networks
A fully rigorous proof of the derivation of Xavier/He's initialization for ReLU nets is given.