GoChat: Goal-oriented Chatbots with Hierarchical Reinforcement Learning

TL;DR

GoChat introduces a hierarchical reinforcement learning framework for goal-oriented chatbots that learn from offline dialogue data, improving response quality and goal success rate without relying on extensive labeled datasets.

Contribution

The paper presents a novel HRL-based framework for training goal-oriented chatbots end-to-end from offline data, reducing reliance on hand-crafted rules and labeled datasets.

Findings

Outperforms previous methods in response quality

Achieves higher success rate in goal completion

Effective in real-world anti-fraud dialogue tasks

Abstract

A chatbot that converses like a human should be goal-oriented (i.e., be purposeful in conversation), which is beyond language generation. However, existing dialogue systems often heavily rely on cumbersome hand-crafted rules or costly labelled datasets to reach the goals. In this paper, we propose Goal-oriented Chatbots (GoChat), a framework for end-to-end training chatbots to maximize the longterm return from offline multi-turn dialogue datasets. Our framework utilizes hierarchical reinforcement learning (HRL), where the high-level policy guides the conversation towards the final goal by determining some sub-goals, and the low-level policy fulfills the sub-goals by generating the corresponding utterance for response. In our experiments on a real-world dialogue dataset for anti-fraud in financial, our approach outperforms previous methods on both the quality of response generation as well as the success rate of accomplishing the goal.