Exploring Zero-Shot ACSA with Unified Meaning Representation in Chain-of-Thought Prompting
This addresses the data scarcity issue in ACSA for domains with limited annotation resources, but it is incremental as it builds on existing CoT methods.
The paper tackled the problem of Aspect-Category Sentiment Analysis (ACSA) in zero-shot settings by proposing a Chain-of-Thought prompting technique with Unified Meaning Representation, finding that its effectiveness may be model-dependent with comparable performance for mid-sized models like Qwen3-8B.
Aspect-Category Sentiment Analysis (ACSA) provides granular insights by identifying specific themes within reviews and their associated sentiment. While supervised learning approaches dominate this field, the scarcity and high cost of annotated data for new domains present significant barriers. We argue that leveraging large language models (LLMs) in a zero-shot setting is a practical alternative where resources for data annotation are limited. In this work, we propose a novel Chain-of-Thought (CoT) prompting technique that utilises an intermediate Unified Meaning Representation (UMR) to structure the reasoning process for the ACSA task. We evaluate this UMR-based approach against a standard CoT baseline across three models (Qwen3-4B, Qwen3-8B, and Gemini-2.5-Pro) and four diverse datasets. Our findings suggest that UMR effectiveness may be model-dependent. Whilst preliminary results indicate comparable performance for mid-sized models such as Qwen3-8B, these observations warrant further investigation, particularly regarding the potential applicability to smaller model architectures. Further research is required to establish the generalisability of these findings across different model scales.