Soft prompt enhanced joint learning for cross-domain aspect-based sentiment analysis

Abstract

Aspect term extraction is a fundamental task in fine-grained sentiment analysis, aiming to detect customer's opinion targets from reviews about products or services. The traditional supervised models have achieved promising results with annotated datasets. However, their performance dramatically decreases in cross-domain aspect term extraction tasks. Existing cross-domain transfer learning methods face two common limitations: (1) these works directly inject linguistic features into language models, making it challenging to transfer linguistic knowledge to the target domain; (2) they rely on the fixed predefined prompts, which is time-consuming to construct the prompts for all potential aspect term spans. To address the limitations, we propose a soft prompt-based joint learning method for cross-domain aspect term extraction in this paper. Specifically, by incorporating external linguistic features, the proposed method learns domain-invariant representations between source and target domains via multiple objectives, which bridges the gap between domains with varied distributions of aspect terms. Furthermore, the proposed method interpolates a set of transferable soft prompts consisting of multiple learnable vectors that are beneficial to detect aspect terms in the target domain. Extensive experiments are conducted on two groups of datasets and the experimental results demonstrate the effectiveness of the proposed method for cross-domain aspect terms extraction.