Zero-Shot Aspect-Based Sentiment Analysis
This addresses the problem of data scarcity in ABSA for researchers and practitioners, offering a novel approach but with incremental improvements in method adaptation.
The paper tackles the challenge of scaling aspect-based sentiment analysis (ABSA) to new domains without annotated data by proposing a unified model for zero-shot ABSA, achieving results that demonstrate ABSA can be conducted without human annotations.
Aspect-based sentiment analysis (ABSA) typically requires in-domain annotated data for supervised training/fine-tuning. It is a big challenge to scale ABSA to a large number of new domains. This paper aims to train a unified model that can perform zero-shot ABSA without using any annotated data for a new domain. We propose a method called contrastive post-training on review Natural Language Inference (CORN). Later ABSA tasks can be cast into NLI for zero-shot transfer. We evaluate CORN on ABSA tasks, ranging from aspect extraction (AE), aspect sentiment classification (ASC), to end-to-end aspect-based sentiment analysis (E2E ABSA), which show ABSA can be conducted without any human annotated ABSA data.