Improving Cross-Domain Performance for Relation Extraction via Dependency Prediction and Information Flow Control

Date and time: 
Friday, January 10, 2020 - 09:30
220 Deschutes
Amir Veyseh
University of Oregon
  • Dejing Dou (Co-Chair)
  • Thien Nguyen (Co-Chair)
  • Daniel Lowd

Relation Extraction (RE) is one of the fundamental tasks in Information Extraction and Natural Language Processing. Dependency trees have been shown to be a very useful source of information for this task. The current deep learning models for relation extraction have mainly exploited this dependency information by guiding their computation along the structures of the dependency trees. One potential problem with this approach is it might prevent the models from capturing important context information beyond syntactic structures and cause the poor cross-domain generalization. This paper introduces a novel method to use dependency trees in RE for deep learning models that jointly predict dependency and semantic relations. We also propose a new mechanism to control the information flow in the model based on the input entity mentions. Our extensive experiments on benchmark datasets show that the proposed model outperforms the existing methods for RE significantly.