Cross-domain aspect-based sentiment analysis (ABSA) aims to perform various fine-grained sentiment analysis tasks on a target domain by transferring knowledge from a source domain. Since labeled data only exists in the source domain, a model is expected to bridge the domain gap for tackling cross-domain ABSA. Though domain adaptation methods have proven to be effective, most of them are based on a discriminative model, which needs to be specifically designed for different ABSA tasks. To offer a more general solution, we propose a unified bidirectional generative framework to tackle various cross-domain ABSA tasks. Specifically, our framework trains a generative model in both text-to-label and label-to-text directions. The former transforms each task into a unified format to learn domain-agnostic features, and the latter generates natural sentences from noisy labels for data augmentation, with which a more accurate model can be trained. To investigate the effectiveness and generality of our framework, we conduct extensive experiments on four cross-domain ABSA tasks and present new state-of-the-art results on all tasks. Our data and code are publicly available at \url{https://github.com/DAMO-NLP-SG/BGCA}.

翻译：跨领域方面级情感分析旨在通过从源领域迁移知识，在目标领域执行各种细粒度情感分析任务。由于标注数据仅存在于源领域，模型需弥合领域差异以应对跨领域ABS任务。尽管领域自适应方法已被证明有效，但多数方法基于判别式模型，需针对不同ABS任务进行专门设计。为提供更通用的解决方案，我们提出统一的双重生成立场框架，以应对多种跨领域ABS任务。具体而言，我们的框架在“文本到标签”和“标签到文本”两个方向训练生成模型：前者将各任务转换为统一格式以学习领域无关特征，后者通过含噪标签生成自然语句以扩充数据，从而训练更精确的模型。为验证框架的有效性和泛化能力，我们在四个跨领域ABS任务上开展广泛实验，并在所有任务上取得新最优结果。我们的数据和代码已开源：\url{https://github.com/DAMO-NLP-SG/BGCA}。