A Unified Model for Opinion Target Extraction and Target Sentiment Prediction

TL;DR

This paper introduces an end-to-end unified neural model for opinion target extraction and sentiment classification, improving accuracy by modeling inter-task dependencies and maintaining sentiment consistency.

Contribution

It presents a novel unified tagging scheme with stacked RNNs, explicit transition modeling, and a gate mechanism for sentiment consistency, advancing target-based sentiment analysis.

Findings

Achieves superior results on three benchmark datasets.

Effectively models inter-task dependencies and sentiment consistency.

Outperforms existing methods in target-based sentiment analysis.

Abstract

Target-based sentiment analysis involves opinion target extraction and target sentiment classification. However, most of the existing works usually studied one of these two sub-tasks alone, which hinders their practical use. This paper aims to solve the complete task of target-based sentiment analysis in an end-to-end fashion, and presents a novel unified model which applies a unified tagging scheme. Our framework involves two stacked recurrent neural networks: The upper one predicts the unified tags to produce the final output results of the primary target-based sentiment analysis; The lower one performs an auxiliary target boundary prediction aiming at guiding the upper network to improve the performance of the primary task. To explore the inter-task dependency, we propose to explicitly model the constrained transitions from target boundaries to target sentiment polarities. We also propose to maintain the sentiment consistency within an opinion target via a gate mechanism which models the relation between the features for the current word and the previous word. We conduct extensive experiments on three benchmark datasets and our framework achieves consistently superior results.