Uncertainty-Aware Unlikelihood Learning Improves Generative Aspect Sentiment Quad Prediction

Understand

Recently, aspect sentiment quad prediction has received widespread attention in the field of aspect-based sentiment analysis.

• Existing studies extract quadruplets via pre-trained generative language models to paraphrase the original sentence into a templated target sequence.
• However, previous works only focus on what to generate but ignore what not to generate.
• We argue that considering the negative samples also leads to potential benefits.