HGSVerb: Improving Zero-shot Text Classification via Hierarchical Generative Semantic-Aware Verbalizer

Prompt-based methods with Pre-trained Language Models (PLMs) have demonstrated remarkable zero-shot performance in text classification tasks. Among these methods, verbalizers are employed to convert model-predicted vocabulary logits into task-specific labels. However, most existing zero-shot approaches face several challenges: (1) a reliance on unlabeled data or additional knowledge bases, which limits their effectiveness in varied data scenarios; (2) a disregard for semantic ambiguity issues in verbalizer construction. This paper presents a novel fully zero-shot approach named Hierarchical Generative Semantic-Aware Generative Verbalizer (HGSVerb). (1) We propose a prompt-based module, Hierarchical Semantic Verbalizer Generation, that explores the full utilization of PLMs and the semantics of label names. As a result, without requiring any extra data or knowledge, our model iteratively generates a verbalizer with hierarchical semantics and structure. (2) We propose a Semantic-Aware Refinement method based on semantic distance between label words and categories to reduce the semantic ambiguity issue. (3) Additionally, HGSVerb introduces a Hierarchical Weight Aggregation to optimize the utilization of our verbalizer by using a decay coefficient to distinguish the importance of label words generated by different iterations. We evaluate HGSVerb on four topic and sentiment classification datasets, and our average accuracy even outperforms those methods utilizing extra resources. We also examine its transferability on datasets with diverse numbers of classes and topics. HGSVerb achieves the best results compared with existing fully zero-shot methods.