Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision (Short Version)
This work addresses the challenge of applying deep learning to complex symbolic reasoning tasks with weak supervision, offering an end-to-end solution that reduces reliance on feature engineering for researchers in natural language processing and AI.
The paper tackles the problem of scaling neural program induction for natural language understanding and symbolic reasoning by proposing the Neural Symbolic Machine framework, which integrates neural networks with non-differentiable memory to learn semantic parsers from weak supervision, achieving new state-of-the-art performance on the WebQuestionsSP dataset.
Extending the success of deep neural networks to natural language understanding and symbolic reasoning requires complex operations and external memory. Recent neural program induction approaches have attempted to address this problem, but are typically limited to differentiable memory, and consequently cannot scale beyond small synthetic tasks. In this work, we propose the Manager-Programmer-Computer framework, which integrates neural networks with non-differentiable memory to support abstract, scalable and precise operations through a friendly neural computer interface. Specifically, we introduce a Neural Symbolic Machine, which contains a sequence-to-sequence neural "programmer", and a non-differentiable "computer" that is a Lisp interpreter with code assist. To successfully apply REINFORCE for training, we augment it with approximate gold programs found by an iterative maximum likelihood training process. NSM is able to learn a semantic parser from weak supervision over a large knowledge base. It achieves new state-of-the-art performance on WebQuestionsSP, a challenging semantic parsing dataset, with weak supervision. Compared to previous approaches, NSM is end-to-end, therefore does not rely on feature engineering or domain specific knowledge.