Aspect-based sentiment analysis (ABSA) aims to predict the sentiment towards a specific aspect in the text. However, existing ABSA test sets cannot be used to probe whether a model can distinguish the sentiment of the target aspect from the non-target aspects. To solve this problem, we develop a simple but effective approach to enrich ABSA test sets. Specifically, we generate new examples to disentangle the confounding sentiments of the non-target aspects from the target aspect's sentiment. Based on the SemEval 2014 dataset, we construct the Aspect Robustness Test Set (ARTS) as a comprehensive probe of the aspect robustness of ABSA models. Over 92% data of ARTS show high fluency and desired sentiment on all aspects by human evaluation. Using ARTS, we analyze the robustness of nine ABSA models, and observe, surprisingly, that their accuracy drops by up to 69.73%. We explore several ways to improve aspect robustness, and find that adversarial training can improve models' performance on ARTS by up to 32.85%. Our code and new test set are available at https://github.com/zhijing-jin/ARTS_TestSet

中文翻译：

---

美味的汉堡、湿透的薯条：在基于方面的情绪分析中探索方面的稳健性

基于方面的情感分析（ABSA）旨在预测对文本中特定方面的情感。然而，现有的 ABSA 测试集不能用于探测模型是否可以区分目标方面和非目标方面的情绪。为了解决这个问题，我们开发了一种简单但有效的方法来丰富 ABSA 测试集。具体来说，我们生成了新的例子来从目标方面的情绪中分离出非目标方面的混淆情绪。基于 SemEval 2014 数据集，我们构建了方面稳健性测试集 (ARTS)，作为对 ABSA 模型方面稳健性的综合探索。超过 92% 的 ARTS 数据通过人工评估显示出各个方面的高度流畅性和期望的情绪。使用 ARTS，我们分析了九个 ABSA 模型的稳健性，并令人惊讶地观察到，他们的准确率下降了 69.73%。我们探索了几种提高方面鲁棒性的方法，发现对抗训练可以将模型在 ARTS 上的性能提高高达 32.85%。我们的代码和新测试集可在 https://github.com/zhijing-jin/ARTS_TestSet 获得