Target-Guided Dialogue Response Generation Using Commonsense and Data Augmentation

TL;DR

This paper presents a novel method for target-guided dialogue response generation that leverages commonsense knowledge and data augmentation to improve control over conversational flow, supported by a new evaluation metric.

Contribution

Introduces a technique using commonsense knowledge paths for transition response generation and re-purposes existing datasets for this task, along with a more reliable evaluation metric.

Findings

Proposed method outperforms baselines in target-guided response generation.

New evaluation metric correlates better with human judgments.

Techniques enable more controlled and goal-oriented dialogue systems.

Abstract

Target-guided response generation enables dialogue systems to smoothly transition a conversation from a dialogue context toward a target sentence. Such control is useful for designing dialogue systems that direct a conversation toward specific goals, such as creating non-obtrusive recommendations or introducing new topics in the conversation. In this paper, we introduce a new technique for target-guided response generation, which first finds a bridging path of commonsense knowledge concepts between the source and the target, and then uses the identified bridging path to generate transition responses. Additionally, we propose techniques to re-purpose existing dialogue datasets for target-guided generation. Experiments reveal that the proposed techniques outperform various baselines on this task. Finally, we observe that the existing automated metrics for this task correlate poorly with human judgement ratings. We propose a novel evaluation metric that we demonstrate is more reliable for target-guided response evaluation. Our work generally enables dialogue system designers to exercise more control over the conversations that their systems produce.