Xiangyu Lin — accepted AI-conference papers

2021

Distantly Supervised Relation Extraction using Multi-Layer Revision Network and Confidence-based Multi-Instance Learning

Xiangyu Lin, Tianyi Liu, Weijia Jia, Zhiguo Gong

EMNLP 2021main

Distantly supervised relation extraction is widely used in the construction of knowledge bases due to its high efficiency. However, the automatically obtained instances are of low quality with numerous irrelevant words. In addition, the strong assumption of distant supervision leads to the existence…

Cited by 13 Source ↗PDF ↗Scholar ↗

2020

Regularized Attentive Capsule Network for Overlapped Relation Extraction

Tianyi Liu, Xiangyu Lin, Weijia Jia, Mingliang Zhou, Wei Zhao

COLING 2020main

Distantly supervised relation extraction has been widely applied in knowledge base construction due to its less requirement of human efforts. However, the automatically established training datasets in distant supervision contain low-quality instances with noisy words and overlapped relations, intro…

Cited by 9 Source ↗PDF ↗Scholar ↗