|国家预印本平台
首页|A Novel Counterfactual Data Augmentation Method for Aspect-Based Sentiment Analysis

A Novel Counterfactual Data Augmentation Method for Aspect-Based Sentiment Analysis

A Novel Counterfactual Data Augmentation Method for Aspect-Based Sentiment Analysis

来源:Arxiv_logoArxiv
英文摘要

Aspect-based-sentiment-analysis (ABSA) is a fine-grained sentiment evaluation task, which analyzes the emotional polarity of the evaluation aspects. Generally, the emotional polarity of an aspect exists in the corresponding opinion expression, whose diversity has great impact on model's performance. To mitigate this problem, we propose a novel and simple counterfactual data augmentation method to generate opinion expressions with reversed sentiment polarity. In particular, the integrated gradients are calculated to locate and mask the opinion expression. Then, a prompt combined with the reverse expression polarity is added to the original text, and a Pre-trained language model (PLM), T5, is finally was employed to predict the masks. The experimental results shows the proposed counterfactual data augmentation method performs better than current augmentation methods on three ABSA datasets, i.e. Laptop, Restaurant, and MAMS.

Zhaoshu Shi、Chao Chen、Dongming Wu、Lulu Wen

计算技术、计算机技术

Zhaoshu Shi,Chao Chen,Dongming Wu,Lulu Wen.A Novel Counterfactual Data Augmentation Method for Aspect-Based Sentiment Analysis[EB/OL].(2023-06-19)[2025-08-03].https://arxiv.org/abs/2306.11260.点此复制

评论