Label-Guided Prompt for Multi-label Few-shot Aspect Category Detection
This work addresses the challenge of identifying multiple aspect categories from sentences with limited training data, which is important for natural language processing applications like sentiment analysis, but it appears incremental as it builds on existing prompt-based approaches.
The paper tackled the problem of multi-label few-shot aspect category detection by proposing a label-guided prompt method to improve sentence and category representations, resulting in a 3.86% to 4.75% improvement in Macro-F1 scores over state-of-the-art methods on two public datasets.
Multi-label few-shot aspect category detection aims at identifying multiple aspect categories from sentences with a limited number of training instances. The representation of sentences and categories is a key issue in this task. Most of current methods extract keywords for the sentence representations and the category representations. Sentences often contain many category-independent words, which leads to suboptimal performance of keyword-based methods. Instead of directly extracting keywords, we propose a label-guided prompt method to represent sentences and categories. To be specific, we design label-specific prompts to represent sentences by combining crucial contextual and semantic information. Further, the label is introduced into a prompt to obtain category descriptions by utilizing a large language model. This kind of category descriptions contain the characteristics of the aspect categories, guiding the construction of discriminative category prototypes. Experimental results on two public datasets show that our method outperforms current state-of-the-art methods with a 3.86% - 4.75% improvement in the Macro-F1 score.