A Speaker Turn-Aware Multi-Task Adversarial Network for Joint User Satisfaction Estimation and Sentiment Analysis

TL;DR

This paper introduces STMAN, a novel multi-task adversarial network that jointly improves user satisfaction estimation and sentiment analysis by effectively distinguishing task-specific and shared features in dialogue systems.

Contribution

The paper proposes a speaker turn-aware multi-task adversarial network that enhances joint learning of satisfaction estimation and sentiment analysis in dialogue systems.

Findings

Outperforms state-of-the-art methods on real-world datasets

Effectively distinguishes task-specific and shared features

Improves dialogue-level satisfaction and utterance-level sentiment analysis

Abstract

User Satisfaction Estimation is an important task and increasingly being applied in goal-oriented dialogue systems to estimate whether the user is satisfied with the service. It is observed that whether the user's needs are met often triggers various sentiments, which can be pertinent to the successful estimation of user satisfaction, and vice versa. Thus, User Satisfaction Estimation (USE) and Sentiment Analysis (SA) should be treated as a joint, collaborative effort, considering the strong connections between the sentiment states of speakers and the user satisfaction. Existing joint learning frameworks mainly unify the two highly pertinent tasks over cascade or shared-bottom implementations, however they fail to distinguish task-specific and common features, which will produce sub-optimal utterance representations for downstream tasks. In this paper, we propose a novel Speaker Turn-Aware Multi-Task Adversarial Network (STMAN) for dialogue-level USE and utterance-level SA. Specifically, we first introduce a multi-task adversarial strategy which trains a task discriminator to make utterance representation more task-specific, and then utilize a speaker-turn aware multi-task interaction strategy to extract the common features which are complementary to each task. Extensive experiments conducted on two real-world service dialogue datasets show that our model outperforms several state-of-the-art methods.