A Corpus-free State2Seq User Simulator for Task-oriented Dialogue

TL;DR

This paper introduces a novel corpus-free State2Seq user simulator for task-oriented dialogue, improving diversity and performance in training dialogue agents without relying on annotated corpora.

Contribution

It proposes a new corpus-free framework and a State2Seq model that leverages dialogue state and history to enhance user simulation for dialogue systems.

Findings

Achieves a 6.36% success rate improvement in agent training

State2Seq outperforms seq2seq baseline with 1.9 F-score increase

Demonstrates effectiveness on an open dataset

Abstract

Recent reinforcement learning algorithms for task-oriented dialogue system absorbs a lot of interest. However, an unavoidable obstacle for training such algorithms is that annotated dialogue corpora are often unavailable. One of the popular approaches addressing this is to train a dialogue agent with a user simulator. Traditional user simulators are built upon a set of dialogue rules and therefore lack response diversity. This severely limits the simulated cases for agent training. Later data-driven user models work better in diversity but suffer from data scarcity problem. To remedy this, we design a new corpus-free framework that taking advantage of their benefits. The framework builds a user simulator by first generating diverse dialogue data from templates and then build a new State2Seq user simulator on the data. To enhance the performance, we propose the State2Seq user simulator model to efficiently leverage dialogue state and history. Experiment results on an open dataset show that our user simulator helps agents achieve an improvement of 6.36% on success rate. State2Seq model outperforms the seq2seq baseline for 1.9 F-score.