Conditional Augmentation for Aspect Term Extraction via Masked Sequence-to-Sequence Generation
This work addresses the lack of annotated data for aspect term extraction in sentiment analysis, offering a domain-specific incremental improvement.
The paper tackles the data scarcity problem in aspect term extraction by proposing a controllable data augmentation method that generates new sentences while preserving original opinion targets and labels, resulting in significant performance boosts for several current models.
Aspect term extraction aims to extract aspect terms from review texts as opinion targets for sentiment analysis. One of the big challenges with this task is the lack of sufficient annotated data. While data augmentation is potentially an effective technique to address the above issue, it is uncontrollable as it may change aspect words and aspect labels unexpectedly. In this paper, we formulate the data augmentation as a conditional generation task: generating a new sentence while preserving the original opinion targets and labels. We propose a masked sequence-to-sequence method for conditional augmentation of aspect term extraction. Unlike existing augmentation approaches, ours is controllable and allows us to generate more diversified sentences. Experimental results confirm that our method alleviates the data scarcity problem significantly. It also effectively boosts the performances of several current models for aspect term extraction.