Chinese Open Relation Extraction with Pointer-Generator Networks
Ziheng Cheng, Xu Wu, Xiaqing Xie, Jingchen Wu · 2020
Most of the traditional Chinese open relation extraction (Open RE) system exploit the syntactic, lexical and other language structure information obtained by natural language processing (NLP) tools from sentences to build hand-crafted patterns for extraction, which is easy to cause error propagation and affect the accuracy of extraction. In this paper, we propose an end-to-end abstract Chinese Open RE model based on the Pointer-Generator network, PGCORE. We employ the results extracted by the state-of-the-art pattern-based Chinese Open RE system as the training set of the model. Experimental results show that our method is outperforms the pattern-based several baselines system, which proves the feasibility and effectiveness of using deep learning models for Chinese Open RE.