Perspectives on neural proof nets
| Autor: | Moot, Richard |
|---|---|
| Rok vydání: | 2022 |
| Předmět: | |
| Zdroj: | End-to-End Compositional Models of Vector-Based Semantics, Aug 2022, Galway, Ireland |
| Druh dokumentu: | Working Paper |
| Popis: | 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. Comment: This is an extended version of an invited talk for the workshop End-to-End Compositional Models of Vector-Based Semantics |
| Databáze: | arXiv |
| Externí odkaz: |
|