Aspect Sentiment Quad Prediction as Paraphrase Generation

By Wenxuan Zhang, Yang Deng, Xin Li, Yifei Yuan, Lidong Bing, Wai Lam. Conference on Empirical Methods in Natural Language Processing, 2021

298 citations recorded by the source corpus.

Aspect-based sentiment analysis (ABSA) has been extensively studied in recent years, which typically involves four fundamental sentiment elements, including the aspect category, aspect term, opinion term, and sentiment polarity. Existing studies usually consider the detection of partial sentiment elements, instead of predicting the four elements in one shot. In this work, we introduce the Aspect Sentiment Quad Prediction (ASQP) task, aiming to jointly detect all sentiment elements in quads for a given opinionated sentence, which can reveal a more comprehensive and complete aspect-level sentiment structure. We further propose a novel Paraphrase modeling paradigm to cast the ASQP task to a paraphrase generation process. On one hand, the generation formulation allows solving ASQP in an end-to-end manner, alleviating the potential error propagation in the pipeline solution. On the other hand, the semantics of the sentiment elements can be fully exploited by learning to generate them in the natural language form. Extensive experiments on benchmark datasets show the superiority of our proposed method and the capacity of cross-task transfer with the proposed unified Paraphrase modeling framework.

View Paper: https://www.semanticscholar.org/paper/85241d5942966f6b5af19f3cf80f7156dbcddf5f

How researchers see this paper

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

1. Xiao Liu
2. Jie Tang
3. Zhilin Yang
4. Lidong Bing
5. Zhengxiao Du
6. Wenxuan Zhang
7. Kaixuan Ji
8. Sinno Jialin Pan

Citations in the corpus

• P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks (2021, background): “Prompting’s advantage and effectiveness in a wide range of NLP applications has been verified in recent literature, including text classification (Hu et al., 2021; Min et al., 2021; Sun et al., 2021; Li et al., 2021; Zhang et al., 2021b), entity typing (Ding et al.”
• Sentiment Analysis in the Era of Large Language Models: A Reality Check (2023, methodology): “Our study utilizes two restaurant datasets from Zhang et al. (2021).”