English

A Bi-directional Multi-hop Inference Model for Joint Dialog Sentiment Classification and Act Recognition

Computation and Language 2023-08-15 v2

Abstract

The joint task of Dialog Sentiment Classification (DSC) and Act Recognition (DAR) aims to predict the sentiment label and act label for each utterance in a dialog simultaneously. However, current methods encode the dialog context in only one direction, which limits their ability to thoroughly comprehend the context. Moreover, these methods overlook the explicit correlations between sentiment and act labels, which leads to an insufficient ability to capture rich sentiment and act clues and hinders effective and accurate reasoning. To address these issues, we propose a Bi-directional Multi-hop Inference Model (BMIM) that leverages a feature selection network and a bi-directional multi-hop inference network to iteratively extract and integrate rich sentiment and act clues in a bi-directional manner. We also employ contrastive learning and dual learning to explicitly model the correlations of sentiment and act labels. Our experiments on two widely-used datasets show that BMIM outperforms state-of-the-art baselines by at least 2.6% on F1 score in DAR and 1.4% on F1 score in DSC. Additionally, Our proposed model not only improves the performance but also enhances the interpretability of the joint sentiment and act prediction task.

Keywords

Cite

@article{arxiv.2308.04424,
  title  = {A Bi-directional Multi-hop Inference Model for Joint Dialog Sentiment Classification and Act Recognition},
  author = {Li Zheng and Fei Li and Yuyang Chai and Chong Teng and Donghong Ji},
  journal= {arXiv preprint arXiv:2308.04424},
  year   = {2023}
}

Comments

Accepted by NLPCC 2023

R2 v1 2026-06-28T11:51:05.917Z