Abstract
Aspect-based sentiment analysis (ABSA), a fine-grained sentiment classification task, has received much attention recently. Many works investigate sentiment information through opinion words, such as ''good'' and ''bad''. However, implicit sentiment widely exists in the ABSA dataset, which refers to the sentence containing no distinct opinion words but still expresses sentiment to the aspect term. To deal with implicit sentiment, this paper proposes an ABSA method that integrates explicit sentiment augmentations. And we propose an ABSA-specific augmentation method to create such augmentations. Specifically, we post-trains T5 by rule-based data. We employ Syntax Distance Weighting and Unlikelihood Contrastive Regularization in the training procedure to guide the model to generate an explicit sentiment. Meanwhile, we utilize the Constrained Beam Search to ensure the augmentation sentence contains the aspect terms. We test ABSA-ESA on two of the most popular benchmarks of ABSA. The results show that ABSA-ESA outperforms the SOTA baselines on implicit and explicit sentiment accuracy.
Abstract (translated)
aspect-based sentiment分析(ABSA)是一种精细情感分类任务,最近受到了很多关注。许多研究通过意见词,如“好”和“坏”,调查情感信息。然而,在ABSA数据集中,隐含情感普遍存在,这指的是没有明确意见词的句子,但仍然对方面表现出了情感。为了处理隐含情感,本文提出了一种将显性情感增强与ABSA方法集成的方法。我们还提出了一种ABSA特定的增强方法来创建这些增强。具体来说,我们通过基于规则的数据对T5进行后训练。我们在训练过程中使用语义距离加权和小概率差异正则化来引导模型生成明确的情感。同时,我们利用约束 beam search 确保增强句子包含方面词汇。我们在两个ABSA最受欢迎的基准上测试ABSA-ESA。结果表明,ABSA-ESA在隐含和显性情感准确率上超过了现有基线。
URL
https://arxiv.org/abs/2312.10961