End-to-end aspect based sentiment analysis (E2E-ABSA) aims to jointly extract aspect terms and predict aspect-level sentiment for opinion reviews. Though supervised methods show effectiveness for E2E-ABSA tasks, the annotation cost is extremely high due to the necessity of fine-grained labels. Recent attempts alleviate this problem using the domain adaptation technique to transfer the word-level common knowledge across domains. However, the biggest issue in domain adaptation, i.e., how to transfer the domain-specific words like pizza and delicious in the source “Restaurant” to the target “Laptop” domain, has not been resolved. In this paper, we propose a novel domain adaptation method to address this issue by enhancing the transferability of domain-specific source words in a retrieve-and-edit way. Specifically, for all source words, we first retrieve the transferable prototypes from unlabeled target data via their syntactic and semantic roles. We then edit the source words to enhance their transferability by absorbing the knowledge carried in prototypes. Finally, we design an end-to-end framework to jointly accomplish cross-domain aspect term extraction and aspect-level sentiment classification. We conduct extensive experiments on four real-world datasets. The results prove that, by introducing transferable prototypes, our method significantly outperforms the state-of-the-art methods, achieving an absolute 3.95% F1 increase over the best baseline.

中文翻译：

---

基于端到端方面的情感分析的检索和编辑域适应


基于端到端方面的情感分析（E2E-ABSA）旨在联合提取方面术语并预测意见评论的方面级别情感。尽管监督方法在 E2E-ABSA 任务中显示出有效性，但由于需要细粒度的标签，注释成本非常高。最近的尝试使用领域适应技术来跨领域传输字级常识来缓解这个问题。然而，域适配中最大的问题，即如何将源“Restaurant”中的pizza、delicious等域特有词转移到目标“Laptop”域中，尚未得到解决。在本文中，我们提出了一种新颖的领域适应方法，通过以检索和编辑的方式增强特定领域源词的可转移性来解决这个问题。具体来说，对于所有源单词，我们首先通过其句法和语义角色从未标记的目标数据中检索可转移原型。然后，我们编辑源词，通过吸收原型中携带的知识来增强其可迁移性。最后，我们设计了一个端到端的框架来共同完成跨领域的方面术语提取和方面级别的情感分类。我们对四个真实世界的数据集进行了广泛的实验。结果证明，通过引入可转移原型，我们的方法显着优于最先进的方法，与最佳基线相比，F1 绝对提高了 3.95%。