Interactive Semantic Parsing for If-Then Recipes via Hierarchical Reinforcement Learning

  • Ziyu Yao The Ohio State University
  • Xiujun Li Microsoft Research
  • Jianfeng Gao Microsoft Research
  • Brian Sadler Army Research Laboratory
  • Huan Sun The Ohio State University

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.1

Published
2019-07-17
Section
AAAI Technical Track: Human-AI Collaboration