Interactive Semantic Parsing for If-Then Recipes via Hierarchical Reinforcement Learning
arXiv:1808.06740
Abstract
Given a text description, most existing semantic parsers synthesize a program in one shot. However, it is quite challenging to produce a correct program solely based on the description, which in reality is often ambiguous or incomplete. In this paper, we investigate interactive semantic parsing, where the agent can ask the user clarification questions to resolve ambiguities via a multi-turn dialogue, on an important type of programs called "If-Then recipes." We develop a hierarchical reinforcement learning (HRL) based agent that significantly improves the parsing performance with minimal questions to the user. Results under both simulation and human evaluation show that our agent substantially outperforms non-interactive semantic parsers and rule-based agents.
arXiv comment13 pages, 2 figures, accepted by AAAI 2019
References in corpus (11)
- Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
- Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
- ReasoNet: Learning to Stop Reading in Machine Comprehension
- A User Simulator for Task-Completion Dialogues
- A Deep Hierarchical Approach to Lifelong Learning in Minecraft
- Language to Logical Form with Neural Attention
- A Syntactic Neural Model for General-Purpose Code Generation
- Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning
- Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning
- Video Captioning via Hierarchical Reinforcement Learning
- Multimodal Hierarchical Reinforcement Learning Policy for Task-Oriented Visual Dialog