Weakly Supervised Reasoning by Neuro-Symbolic Approaches
This work addresses the need for interpretable AI in NLP, but it appears incremental as it builds on existing neuro-symbolic methods without claiming major breakthroughs.
The paper tackles the problem of black-box deep learning models lacking explicit interpretation in NLP by introducing neuro-symbolic approaches that combine symbolism and connectionism, resulting in a framework successfully applied to tasks like table query reasoning and syntactic structure reasoning with experimental results.
Deep learning has largely improved the performance of various natural language processing (NLP) tasks. However, most deep learning models are black-box machinery, and lack explicit interpretation. In this chapter, we will introduce our recent progress on neuro-symbolic approaches to NLP, which combines different schools of AI, namely, symbolism and connectionism. Generally, we will design a neural system with symbolic latent structures for an NLP task, and apply reinforcement learning or its relaxation to perform weakly supervised reasoning in the downstream task. Our framework has been successfully applied to various tasks, including table query reasoning, syntactic structure reasoning, information extraction reasoning, and rule reasoning. For each application, we will introduce the background, our approach, and experimental results.