关于神经证明网的观点
Perspectives on neural proof nets
摘要:
在本文中,我将提出一种新的方法相结合的证明网络证明搜索与神经网络。它与“标准”方法形成对比,该方法已被应用于以各种不同形式的类型逻辑语法的证明搜索。在标准方法中,我们首先将单词转换为公式(超级标记),然后匹配原子公式以获得证明。我将介绍一种将任务分成两部分的替代方法:首先,我们以保证它对应于一个顶点项的方式生成图结构,然后我们使用顶点标记来获得详细的结构。顶点标记是图神经网络中的一个研究得很好的任务,并且将探索使用神经网络实现图生成的不同方式。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。