LACA：利用LLM数据增强改进跨语言基于方面的情感分析
LACA: Improving Cross-lingual Aspect-Based Sentiment Analysis with LLM Data Augmentation
AI总结：
提出LACA框架，利用LLM生成高质量伪标注数据替代翻译工具，通过训练ABSA模型预测并生成自然句子进行微调，在六种语言和五个模型上超越现有翻译方法。
摘要：
跨语言基于方面的情感分析（ABSA）涉及通过从具有可用标注数据的源语言迁移知识，在目标语言中进行详细的情感分析。现有大多数方法严重依赖通常不可靠的翻译工具来弥合语言鸿沟。在本文中，我们提出了一种新方法，利用大型语言模型（LLM）在目标语言中生成高质量的伪标注数据，而无需翻译工具。首先，该框架训练一个ABSA模型以获得未标注目标语言数据的预测。接着，提示LLM生成比原始文本更能代表这些噪声预测的自然句子。然后，在生成的伪标注数据集上进一步微调ABSA模型。我们证明了该方法在六种语言和五个骨干模型上的有效性，超越了以往基于翻译的最先进方法。该框架还支持生成式模型，并表明微调后的LLM优于较小的多语言模型。
英文摘要：
Cross-lingual aspect-based sentiment analysis (ABSA) involves detailed sentiment analysis in a target language by transferring knowledge from a source language with available annotated data. Most existing methods depend heavily on often unreliable translation tools to bridge the language gap. In this paper, we propose a new approach that leverages a large language model (LLM) to generate high-quality pseudo-labelled data in the target language without the need for translation tools. First, the framework trains an ABSA model to obtain predictions for unlabelled target language data. Next, LLM is prompted to generate natural sentences that better represent these noisy predictions than the original text. The ABSA model is then further fine-tuned on the resulting pseudo-labelled dataset. We demonstrate the effectiveness of this method across six languages and five backbone models, surpassing previous state-of-the-art translation-based approaches. The proposed framework also supports generative models, and we show that fine-tuned LLMs outperform smaller multilingual models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
