Exploiting Unlabeled Data for Target-Oriented Opinion Words Extraction

TL;DR

This paper introduces a novel semi-supervised learning method called MGCR that leverages unlabeled data with consistency regularization and filtering to improve target-oriented opinion words extraction, outperforming existing methods.

Contribution

It proposes a new Multi-Grained Consistency Regularization approach with filtering techniques to effectively utilize unlabeled data for TOWE, addressing data scarcity and distribution shift issues.

Findings

MGCR outperforms state-of-the-art methods on four benchmarks.

Filtering noisy data improves model robustness.

Unlabeled data enhances the model's ability to handle distribution shifts.

Abstract

Target-oriented Opinion Words Extraction (TOWE) is a fine-grained sentiment analysis task that aims to extract the corresponding opinion words of a given opinion target from the sentence. Recently, deep learning approaches have made remarkable progress on this task. Nevertheless, the TOWE task still suffers from the scarcity of training data due to the expensive data annotation process. Limited labeled data increase the risk of distribution shift between test data and training data. In this paper, we propose exploiting massive unlabeled data to reduce the risk by increasing the exposure of the model to varying distribution shifts. Specifically, we propose a novel Multi-Grained Consistency Regularization (MGCR) method to make use of unlabeled data and design two filters specifically for TOWE to filter noisy data at different granularity. Extensive experimental results on four TOWE benchmark datasets indicate the superiority of MGCR compared with current state-of-the-art methods. The in-depth analysis also demonstrates the effectiveness of the different-granularity filters. Our codes are available at https://github.com/TOWESSL/TOWESSL.