Opinion Transmission Network for Jointly Improving Aspect-oriented Opinion Words Extraction and Sentiment Classification

TL;DR

This paper introduces a joint opinion transmission network that simultaneously improves aspect-level sentiment classification and opinion words extraction by leveraging their interconnections through bidirectional opinion flow mechanisms.

Contribution

The paper proposes a novel joint model with opinion transmission mechanisms that connect ALSC and AOWE, enhancing their performance together.

Findings

Outperforms strong baselines on benchmark datasets

Bidirectional opinion transmission improves task performance

Mechanisms are validated through extensive analysis

Abstract

Aspect-level sentiment classification (ALSC) and aspect oriented opinion words extraction (AOWE) are two highly relevant aspect-based sentiment analysis (ABSA) subtasks. They respectively aim to detect the sentiment polarity and extract the corresponding opinion words toward a given aspect in a sentence. Previous works separate them and focus on one of them by training neural models on small-scale labeled data, while neglecting the connections between them. In this paper, we propose a novel joint model, Opinion Transmission Network (OTN), to exploit the potential bridge between ALSC and AOWE to achieve the goal of facilitating them simultaneously. Specifically, we design two tailor-made opinion transmission mechanisms to control opinion clues flow bidirectionally, respectively from ALSC to AOWE and AOWE to ALSC. Experiment results on two benchmark datasets show that our joint model outperforms strong baselines on the two tasks. Further analysis also validates the effectiveness of opinion transmission mechanisms.