Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

8-2021

Abstract

Aspect-based sentiment analysis (ABSA) has received increasing attention recently. Most existing work tackles ABSA in a discriminative manner, designing various task-specific classification networks for the prediction. Despite their effectiveness, these methods ignore the rich label semantics in ABSA problems and require extensive task-specific designs. In this paper, we propose to tackle various ABSA tasks in a unified generative framework. Two types of paradigms, namely annotation-style and extraction-style modeling, are designed to enable the training process by formulating each ABSA task as a text generation problem. We conduct experiments on four ABSA tasks across multiple benchmark datasets where our proposed generative approach achieves new state-of-the-art results in almost all cases. This also validates the strong generality of the proposed framework which can be easily adapted to arbitrary ABSA task without additional taskspecific model design.1.

Keywords

Analysis problems, Benchmark datasets, Classification networks, Label semantics, Sentiment analysis, State of the art, Task-specific models, Text generations, Training process

Discipline

Databases and Information Systems | Graphics and Human Computer Interfaces | Information Security

Research Areas

Data Science and Engineering

Areas of Excellence

Digital transformation

Publication

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Virtual, Online, 2021 August 1-6

First Page

504

Last Page

510

ISBN

9781954085527

Identifier

10.18653/v1/2021.acl-short.64

Publisher

Association for Computational Linguistics

City or Country

Texas

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.18653/v1/2021.acl-short.64

Download

Share

COinS