DARER: Dual-task Temporal Relational Recurrent Reasoning Network for Joint Dialog Sentiment Classification and Act Recognition

TL;DR

DARER is a novel framework that models explicit dependencies at the prediction level for joint dialog sentiment and act recognition, utilizing temporal and relational graphs to improve accuracy and efficiency.

Contribution

It introduces a new dual-task relational temporal graph and a prediction-level interaction mechanism, advancing dialog understanding with less computational cost.

Findings

Outperforms existing models significantly in F1 score on Mastodon dataset.

Requires less computation resources and training time.

Achieves about 25% relative improvement in F1 score.

Abstract

The task of joint dialog sentiment classification (DSC) and act recognition (DAR) aims to simultaneously predict the sentiment label and act label for each utterance in a dialog. In this paper, we put forward a new framework which models the explicit dependencies via integrating \textit{prediction-level interactions} other than semantics-level interactions, more consistent with human intuition. Besides, we propose a speaker-aware temporal graph (SATG) and a dual-task relational temporal graph (DRTG) to introduce \textit{temporal relations} into dialog understanding and dual-task reasoning. To implement our framework, we propose a novel model dubbed DARER, which first generates the context-, speaker- and temporal-sensitive utterance representations via modeling SATG, then conducts recurrent dual-task relational reasoning on DRTG, in which process the estimated label distributions act as key clues in prediction-level interactions. Experiment results show that DARER outperforms existing models by large margins while requiring much less computation resource and costing less training time. Remarkably, on DSC task in Mastodon, DARER gains a relative improvement of about 25% over previous best model in terms of F1, with less than 50% parameters and about only 60% required GPU memory.