Few-Shot Relation Extraction on Ancient Chinese Documents

Abstract

Traditional humanity scholars’ inefficient method of utilizing numerous unstructured data has hampered studies on ancient Chinese writings for several years. In this work, we aim to develop a relation extractor for ancient Chinese documents to automatically extract the relations by using unstructured data. To achieve this goal, we proposed a tiny ancient Chinese document relation classification (TinyACD-RC) dataset annotated by historians and contains 32 types of general relations in ShihChi (a famous Chinese history book). We also explored several methods and proposed a novel model that works well on sufficient and insufficient data scenarios, the proposed sentence encoder can simultaneously capture local and global features for a certain period. The paired attention network enhances and extracts relations between support and query instances. Experimental results show that our model achieved promising performance with scarce corpus. We also examined our model on the FewRel dataset and found that outperformed the state-of-the-art no pretraining-based models by 2.27%.

Keywords

• ancient Chinese document
• relation extraction
• few-shot learning
• sentence encoder
• digital humanity