Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision
Preprint
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.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Learning to Skim Text2017
- Hybrid computing using a neural network with dynamic external memoryNature, 2016
- Deep Reinforcement Learning for Dialogue Generation2016
- Language to Logical Form with Neural Attention2016
- Learning to Compose Neural Networks for Question Answering2016
- Sequence-to-Sequence Learning as Beam-Search Optimization2016
- Imitation Learning of Agenda-based Semantic ParsersTransactions of the Association for Computational Linguistics, 2015
- Semantic Parsing on Freebase from Question-Answer Pairs2013
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012
- Optimal Ordered Problem SolverMachine Learning, 2004