From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood
This addresses the challenge of training semantic parsers without direct program labels, which is incremental as it builds on existing RL and MML methods.
The paper tackles the problem of learning semantic parsers from indirect supervision, where only execution results are given, by combining reinforcement learning and maximum marginal likelihood to mitigate spurious programs. It achieves significant gains over state-of-the-art results on a context-dependent semantic parsing task.
Our goal is to learn a semantic parser that maps natural language utterances into executable programs when only indirect supervision is available: examples are labeled with the correct execution result, but not the program itself. Consequently, we must search the space of programs for those that output the correct result, while not being misled by spurious programs: incorrect programs that coincidentally output the correct result. We connect two common learning paradigms, reinforcement learning (RL) and maximum marginal likelihood (MML), and then present a new learning algorithm that combines the strengths of both. The new algorithm guards against spurious programs by combining the systematic search traditionally employed in MML with the randomized exploration of RL, and by updating parameters such that probability is spread more evenly across consistent programs. We apply our learning algorithm to a new neural semantic parser and show significant gains over existing state-of-the-art results on a recent context-dependent semantic parsing task.