Cross-Relation Cross-Bag Attention for Distantly-Supervised Relation Extraction


  • Yujin Yuan Zhejiang University
  • Liyuan Liu University of Illinois at Urbana Champaign
  • Siliang Tang Zhejiang University
  • Zhongfei Zhang Zhejiang University
  • Yueting Zhuang Zhejiang University
  • Shiliang Pu Hikvision Research Institute
  • Fei Wu Zhejiang University
  • Xiang Ren University of Southern California



Distant supervision leverages knowledge bases to automatically label instances, thus allowing us to train relation extractor without human annotations. However, the generated training data typically contain massive noise, and may result in poor performances with the vanilla supervised learning. In this paper, we propose to conduct multi-instance learning with a novel Cross-relation Cross-bag Selective Attention (C2SA), which leads to noise-robust training for distant supervised relation extractor. Specifically, we employ the sentence-level selective attention to reduce the effect of noisy or mismatched sentences, while the correlation among relations were captured to improve the quality of attention weights. Moreover, instead of treating all entity-pairs equally, we try to pay more attention to entity-pairs with a higher quality. Similarly, we adopt the selective attention mechanism to achieve this goal. Experiments with two types of relation extractor demonstrate the superiority of the proposed approach over the state-of-the-art, while further ablation studies verify our intuitions and demonstrate the effectiveness of our proposed two techniques.




How to Cite

Yuan, Y., Liu, L., Tang, S., Zhang, Z., Zhuang, Y., Pu, S., Wu, F., & Ren, X. (2019). Cross-Relation Cross-Bag Attention for Distantly-Supervised Relation Extraction. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 419-426.



AAAI Technical Track: AI and the Web