DCR-Net: A Deep Co-Interactive Relation Network for Joint Dialog Act Recognition and Sentiment Classification

TL;DR

This paper introduces DCR-Net, a novel deep network that explicitly models the interaction between dialog act recognition and sentiment classification, leading to improved performance on public datasets by capturing mutual influence through multi-step relation layers.

Contribution

The paper proposes a co-interactive relation layer within DCR-Net that explicitly models task interactions and employs multi-step interaction, enhancing joint dialog understanding.

Findings

Outperforms state-of-the-art models on Mastodon and Dailydialog datasets.

Explicit relation modeling improves dialog act and sentiment classification accuracy.

Multi-step interaction captures mutual knowledge effectively.

Abstract

In dialog system, dialog act recognition and sentiment classification are two correlative tasks to capture speakers intentions, where dialog act and sentiment can indicate the explicit and the implicit intentions separately. Most of the existing systems either treat them as separate tasks or just jointly model the two tasks by sharing parameters in an implicit way without explicitly modeling mutual interaction and relation. To address this problem, we propose a Deep Co-Interactive Relation Network (DCR-Net) to explicitly consider the cross-impact and model the interaction between the two tasks by introducing a co-interactive relation layer. In addition, the proposed relation layer can be stacked to gradually capture mutual knowledge with multiple steps of interaction. Especially, we thoroughly study different relation layers and their effects. Experimental results on two public datasets (Mastodon and Dailydialog) show that our model outperforms the state-of-the-art joint model by 4.3% and 3.4% in terms of F1 score on dialog act recognition task, 5.7% and 12.4% on sentiment classification respectively. Comprehensive analysis empirically verifies the effectiveness of explicitly modeling the relation between the two tasks and the multi-steps interaction mechanism. Finally, we employ the Bidirectional Encoder Representation from Transformer (BERT) in our framework, which can further boost our performance in both tasks.