Publications

Exploring Conditional Text Generation for Aspect-based Sentiment Analysis

PACLIC 2021

Publication date: November 7, 2021

Siva Uday Sampreeth Chebolu‬, Franck Dernoncourt, Nedim Lipka, Thamar Solorio

Aspect-based sentiment analysis (ABSA) is a task that entails evaluating reviews to determine the target being evaluated, the category to which it belongs, and the sentiment expressed towards the target and aspect pair. In this article, we use these targets, aspects, and polarities to generate auxiliary statements, transforming ABSA into an abstract summary-like conditional text generation task. To demonstrate the efficacy of our formulation and proposed system, we fine-tune a pre-trained model for conditional text generation task to get new state-of-the-art results on a few restaurant domain and urban neighborhoods domain benchmark datasets.