EATN: An Efficient Adaptive Transfer Network for Aspect-Level Sentiment Analysis

Aspect-level sentiment analysis is a granular emotional classification task that refers to identifying sentiment polarities towards aspects in a sentence. Although previous research has reached a great achievement, this task remains very challenging. First, previous approaches only focus on one specific domain, which lacks the capability of transferring to other domains. Moreover, the majority of prior studies ignore the direct relationship between aspects and the corresponding sentiment words. To this end, in this paper, we propose a novel model named Efficient Adaptive Transfer Network (EATN) for aspect-level sentiment analysis which emphasizes the need to incorporate the correlation among multiple domains. The proposed EATN provides a Domain Adaptation Module (DAM) to learn common features from the sufficiently labelled source domain and guide the target domain's classification performance. Specifically, DAM comprises two special tasks, with one sentiment classification task aiming to learn sentiment knowledge and the other domain classification task focusing on learning domain-invariant features. Here, we adopt a multiple-kernel selection method to further reduce the feature discrepancy among domains. Besides that, EATN contains a novel aspect-oriented multi-head attention to capture the direct associations between the aspects and the contextual sentiment words, which is beneficial to learn the aspect-aware semantic knowledge. Extensive experiments on six public datasets with two granularities, compared with current state-of-the-art methods, demonstrate the effectiveness and universality of our method.