login
Home / Papers / Towards Generative Aspect-Based Sentiment Analysis

Towards Generative Aspect-Based Sentiment Analysis

183 Citations2021
Wenxuan Zhang, Xin Li, Yang Deng
journal unavailable

This paper proposes to tackle various ABSA tasks in a unified generative framework with two types of paradigms, namely annotation-style and extraction-style modeling, to enable the training process by formulating each ABSA task as a text generation problem.

Abstract

Wenxuan Zhang, Xin Li, Yang Deng, Lidong Bing, Wai Lam. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers). 2021.