Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision

TL;DR

This paper introduces a Neural Symbolic Machine that combines neural networks and symbolic reasoning to improve semantic parsing on Freebase using weak supervision, achieving state-of-the-art results.

Contribution

It presents a novel neural-symbolic framework with a neural programmer and symbolic executor, trained with reinforcement learning and maximum likelihood, for semantic parsing.

Findings

Outperforms previous state-of-the-art on WebQuestionsSP dataset

Effective training with weak supervision and reinforcement learning

No feature engineering or domain-specific knowledge needed

Abstract

Harnessing the statistical power of neural networks to perform language understanding and symbolic reasoning is difficult, when it requires executing efficient discrete operations against a large knowledge-base. In this work, we introduce a Neural Symbolic Machine, which contains (a) a neural "programmer", i.e., a sequence-to-sequence model that maps language utterances to programs and utilizes a key-variable memory to handle compositionality (b) a symbolic "computer", i.e., a Lisp interpreter that performs program execution, and helps find good programs by pruning the search space. We apply REINFORCE to directly optimize the task reward of this structured prediction problem. To train with weak supervision and improve the stability of REINFORCE, we augment it with an iterative maximum-likelihood training process. NSM outperforms the state-of-the-art on the WebQuestionsSP dataset when trained from question-answer pairs only, without requiring any feature engineering or domain-specific knowledge.