Abstract: Aspect Category Sentiment Analysis (ACSA) is currently constrained by the scarcity of annotated data, making it a research challenge to achieve effective analysis without specific sentiment-labeled data. This paper transforms the zero-shot ACSA task into a Natural Language Inference (NLI) task. Addressing the issue of inadequate semantic expression in traditional prompt templates, we propose a novel cause supplementation prompt template based on the Plug and Play Language Model (PPLM) for text restriction generation. By combining sentiment polarity with its causes, the template helps the model better understand the reasons and motivations behind the sentiments, thereby improving the accuracy and interpretability of sentiment analysis. Furthermore, to enhance the classification performance of ACSA, we introduce the performance inversion coefficient to determine the ensemble weights of various prompt templates in the paper. Experimental results on the public datasets MAMS and Restaurant demonstrate that our model outperforms other zero-shot ACSA models by approximately 7% in accuracy. The PPLM cause supplementation prompt template can enhance the zero-shot classification performance of NLI models, showing a 2.5% improvement in Macro F1 score compared to other traditional templates. Additionally, the improved weight determination strategy also contributes to the model's sentiment analysis capability in zero-shot scenarios.

Key words: Aspect-based Sentiment Analysis, Zero-shot Learning, Prompt Template, PPLM Text-conditioned Generation

摘要： 如今方面类别情感分析(Aspect Category Sentiment Analysis,ACSA)因标注数据稀缺而受限，如何在无特定情感标注数据下实现有效分析成为研究挑战。本文将零样本方面类别情感分析任务转换为自然语言推理(Natural Language Inference,NLI)任务，针对传统提示模板面临着语义表达不充分的问题，新提出了一种基于PPLM(Plug and Play Language Model)文本限制生成模型的原因补充提示模板，通过结合情感极性和其原因，使得模板可以帮助模型更好地理解情感背后的原因和动机，从而提高情感分析的准确性和可解释性，此外为了进一步提升ACSA的分类性能，引入了性能逆序系数来确定文中多种提示模板的集成权重。在公共数据集MAMS和Restaurant的实验结果表明本文模型相较于其他零样本ACSA模型，在准确率ACC上提升约7%；PPLM原因补充提示模板可以提升NLI模型的零样本分类性能，其相较于其他传统模板在MF1上提升2.5%；同时改进的权重确定策略也对模型在零样本情境下的情感分析能力有一定提升作用。

关键词: 方面类别情感分析, 零样本学习, 提示模板, PPLM文本限制生成