Adaptive Prompt Learning-based Few-Shot Sentiment Analysis
This work addresses the challenge of insufficient labeled data for sentiment analysis in NLP, offering a method to improve few-shot learning performance, though it appears incremental as it builds on existing prompt learning techniques.
The paper tackles the problem of data deficiency in sentiment analysis by proposing an adaptive prompting construction strategy that dynamically generates prompts using a seq2seq-attention structure, and it demonstrates effectiveness by outperforming state-of-the-art baselines on FewCLUE datasets.
In the field of natural language processing, sentiment analysis via deep learning has a excellent performance by using large labeled datasets. Meanwhile, labeled data are insufficient in many sentiment analysis, and obtaining these data is time-consuming and laborious. Prompt learning devotes to resolving the data deficiency by reformulating downstream tasks with the help of prompt. In this way, the appropriate prompt is very important for the performance of the model. This paper proposes an adaptive prompting(AP) construction strategy using seq2seq-attention structure to acquire the semantic information of the input sequence. Then dynamically construct adaptive prompt which can not only improve the quality of the prompt, but also can effectively generalize to other fields by pre-trained prompt which is constructed by existing public labeled data. The experimental results on FewCLUE datasets demonstrate that the proposed method AP can effectively construct appropriate adaptive prompt regardless of the quality of hand-crafted prompt and outperform the state-of-the-art baselines.