论文标题
关于神经证明网的观点
Perspectives on neural proof nets
论文作者
论文摘要
在本文中，我将提出一种将证明网络搜索与神经网络相结合的新颖方式。它与已应用于以各种不同形式的类型语法进行证明搜索的“标准”方法形成鲜明对比。在标准方法中，我们首先将单词转换为公式（超索），然后匹配原子公式以获得证明。我将介绍一种将任务分为两个的替代方法：首先，我们以保证其对应于lambda-Term的方式生成图形结构，然后我们使用顶点标签获得详细的结构。顶点标签是图神经网络中的一项良好的任务，将探索使用神经网络实现图生成的不同方式。
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.
