A Unified Generative Framework for Aspect-based Sentiment Analysis

By Hang Yan, Junqi Dai, Tuo Ji, Xipeng Qiu, Zheng Zhang. Annual Meeting of the Association for Computational Linguistics, 2021

371 citations recorded by the source corpus.

Aspect-based Sentiment Analysis (ABSA) aims to identify the aspect terms, their corresponding sentiment polarities, and the opinion terms. There exist seven subtasks in ABSA. Most studies only focus on the subsets of these subtasks, which leads to various complicated ABSA models while hard to solve these subtasks in a unified framework. In this paper, we redefine every subtask target as a sequence mixed by pointer indexes and sentiment class indexes, which converts all ABSA subtasks into a unified generative formulation. Based on the unified formulation, we exploit the pre-training sequence-to-sequence model BART to solve all ABSA subtasks in an end-to-end framework. Extensive experiments on four ABSA datasets for seven subtasks demonstrate that our framework achieves substantial performance gain and provides a real unified end-to-end solution for the whole ABSA subtasks, which could benefit multiple tasks.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/968820dfae97f80b63674fd76cd7d82332498708

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Wenxuan Zhang
2. Lidong Bing
3. Wai Lam
4. Xin Li
5. Yang Deng
6. Yifei Yuan
7. Yaojie Lu
8. Xinyan Xiao

Citations in the corpus

• Aspect Sentiment Quad Prediction as Paraphrase Generation (2021, background): “Very recently, there are some attempts on tackling ABSA problem in a S2S manner, either treating the class index (Yan et al., 2021) or the desired sentiment element sequence (Zhang et al., 2021) as the target of the generation model.”
• A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges (2022, methodology): “End-to-End ABSA NN-CRF [79] Dual-MRC [95] Gen-ABSA [97] SPAN [84]”
• Unified Structure Generation for Universal Information Extraction (2022, methodology): “…relevant to our work are generation-based IE methods, which generate text spans via tagging (Straková et al., 2019; Ma et al., 2019), index pointer (Ren et al., 2021; Yan et al., 2021b) or copy mechanism (Zeng et al., 2018), and these methods usually employ specific classifiers to represent labels.”
• Retrieval And Structuring Augmented Generation with Large Language Models (2025, unknown): “Similarly, frameworks like REBEL [83] and ABSA [271] leverage pre-trained language models (PLMs) to translate raw text into structured knowledge.”