Solving Aspect Category Sentiment Analysis as a Text Generation Task (2110.07310v1)

Abstract: Aspect category sentiment analysis has attracted increasing research attention. The dominant methods make use of pre-trained LLMs by learning effective aspect category-specific representations, and adding specific output layers to its pre-trained representation. We consider a more direct way of making use of pre-trained LLMs, by casting the ACSA tasks into natural language generation tasks, using natural language sentences to represent the output. Our method allows more direct use of pre-trained knowledge in seq2seq LLMs by directly following the task setting during pre-training. Experiments on several benchmarks show that our method gives the best reported results, having large advantages in few-shot and zero-shot settings.