arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2311.05922cs.CL
收藏

面向少样本关系抽取的带显式证据推理的思维链

Chain of Thought with Explicit Evidence Reasoning for Few-shot Relation Extraction

Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳))

Xilai Ma, Jing Li, Min Zhang

AI总结:

针对少样本关系抽取中思维链提示缺乏显式推理证据的问题,提出CoT-ER方法,通过生成并显式融入任务与概念级证据,在零训练数据下达到与全监督最优方法相当的性能。

摘要:

少样本关系抽取旨在利用有限数量的标注样本,识别文本中两个特定实体之间的关系类型。针对该问题已涌现出多种采用元学习和神经图技术的解决方案,这些方法通常需要训练过程来完成适配。近期,上下文学习策略在无需训练的情况下展现出显著效果,已有少量研究将上下文学习用于零样本信息抽取。遗憾的是,在构建思维链提示的过程中,推理证据要么未被考虑,要么仅被隐式建模。本文提出一种利用大语言模型开展少样本关系抽取的新方法,名为CoT-ER(带显式证据推理的思维链)。具体而言,CoT-ER首先引导大语言模型利用任务特定知识和概念层面知识生成证据,随后将这些证据显式融入思维链提示中以开展关系抽取。实验结果表明,在FewRel1.0和FewRel2.0数据集上,本文的CoT-ER方法(使用0%训练数据)取得了与采用100%训练数据的全监督最优方法相当的性能。

英文摘要:

Few-shot relation extraction involves identifying the type of relationship between two specific entities within a text, using a limited number of annotated samples. A variety of solutions to this problem have emerged by applying meta-learning and neural graph techniques which typically necessitate a training process for adaptation. Recently, the strategy of in-context learning has been demonstrating notable results without the need of training. Few studies have already utilized in-context learning for zero-shot information extraction. Unfortunately, the evidence for inference is either not considered or implicitly modeled during the construction of chain-of-thought prompts. In this paper, we propose a novel approach for few-shot relation extraction using large language models, named CoT-ER, chain-of-thought with explicit evidence reasoning. In particular, CoT-ER first induces large language models to generate evidences using task-specific and concept-level knowledge. Then these evidences are explicitly incorporated into chain-of-thought prompting for relation extraction. Experimental results demonstrate that our CoT-ER approach (with 0% training data) achieves competitive performance compared to the fully-supervised (with 100% training data) state-of-the-art approach on the FewRel1.0 and FewRel2.0 datasets.

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。

↑