YAYI-UIE：面向通用信息抽取的对话增强指令微调框架
YAYI-UIE: A Chat-Enhanced Instruction Tuning Framework for Universal Information Extraction
AI总结：
本文提出YAYI-UIE框架，通过对话增强指令微调联合利用对话与信息抽取数据，在中文数据集上取得最优性能，并在英文数据集上表现可比。
摘要：
信息抽取任务的难点在于处理任务特定的标签模式和异构数据结构。近期工作提出了基于大语言模型的方法，以统一建模不同的信息抽取任务。然而，这些现有方法在英语以外的中文信息抽取能力上存在不足。本文提出了一种端到端的对话增强指令微调框架，用于通用信息抽取（YAYI-UIE），同时支持中文和英文。具体而言，我们利用对话数据和信息抽取数据来联合提升信息抽取性能。实验结果表明，我们提出的框架在有监督设置和零样本设置下，在中文数据集上取得了最先进的性能，同时在英文数据集上也取得了可比的性能。
英文摘要：
The difficulty of the information extraction task lies in dealing with the task-specific label schemas and heterogeneous data structures. Recent work has proposed methods based on large language models to uniformly model different information extraction tasks. However, these existing methods are deficient in their information extraction capabilities for Chinese languages other than English. In this paper, we propose an end-to-end chat-enhanced instruction tuning framework for universal information extraction (YAYI-UIE), which supports both Chinese and English. Specifically, we utilize dialogue data and information extraction data to enhance the information extraction performance jointly. Experimental results show that our proposed framework achieves state-of-the-art performance on Chinese datasets while also achieving comparable performance on English datasets under both supervised settings and zero-shot settings.
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。
