UniRE: A Unified Label Space for Entity Relation Extraction

Authors:
  • YWYijun Wang
    Yijun Wang
  • CSChangzhi Sun
    Changzhi Sun
  • YWYuanbin Wu
    Yuanbin Wu
  • HZHao Zhou
    Hao Zhou
  • LLLei Li
    Lei Li
  • JYJunchi Yan
    Junchi Yan

Abstract
Many joint entity relation extraction models setup two separated label spaces for the two sub-tasks (i.e., entity detection and relation classification). We argue that this setting may hinder the information interaction between entities and relations. In this work, we propose to eliminate the different treatment on the two sub-tasks' label spaces. The input of our model is a table containing all word pairs from a sentence. Entities and relations are represented by squares and rectangles in the table. We apply a unified classifier to predict each cell's label, which unifies the learning of two sub-tasks. For testing, an effective (yet fast) approximate decoder is proposed for finding squares and rectangles from tables. Experiments on three benchmarks (ACE04, ACE05, SciERC) show that, using only half the number of parameters, our model achieves competitive accuracy with the best extractor, and is faster.
All Related Versions