Abstract
Aspect Sentiment Triplet Extraction (ASTE) is a subtask of Aspect-Based Sentiment Analysis (ABSA) that considers each opinion term, their expressed sentiment, and the corresponding aspect targets. However, existing methods are limited to the in-domain setting with two domains. Hence, we propose a domain-expanded benchmark to address the in-domain, out-of-domain and cross-domain settings. We support the new benchmark by annotating more than 4000 data samples for two new domains based on hotel and cosmetics reviews. Our analysis of five existing methods shows that while there is a significant gap between in-domain and out-of-domain performance, generative methods have a strong potential for domain generalization. Our datasets, code implementation and models are available at this https URL .
Abstract (translated)
Aspect SentimentTriplet Extraction(ASTE)是 aspect-based Sentiment Analysis(ABSA)的一个子任务,它考虑每个观点术语、它们表达的情感以及相应的 aspect 目标。然而,现有的方法局限于两个域内的情况。因此,我们提出了一个域扩展基准,以解决域内、域间和跨域情况。我们支持新的基准,通过为基于酒店和化妆品评论的两个新域标注超过4000个数据样本。我们对五种现有方法进行了分析,表明虽然域内和域间表现之间存在显著差距,生成方法具有域泛化的强大潜力。我们的数据集、代码实现和模型可在 this https:// URL 上获取。
URL
https://arxiv.org/abs/2305.14434