Conference Papers Year : 2022

Augmenting Context Representation with Triggers Knowledge for Relation Extraction

En Li
  • Function : Author
  • PersonId : 1275201
Shumin Shi
  • Function : Author
  • PersonId : 1275202
Zhikun Yang
  • Function : Author
  • PersonId : 1275203
He Yan Huang
  • Function : Author
  • PersonId : 1275204

Abstract

Relation Extraction (RE) requires the model to classify the correct relation from a set of relation candidates given the corresponding sentence and two entities. Recent work mainly studies how to utilize more data or incorporate extra context information especially with Pre-trained Language Models (PLMs). However, these models still face with the challenges of avoiding being affected by irrelevant or misleading words. In this paper, we propose a novel model to help alleviate such deficiency. Specifically, our model automatically mines the triggers of the sentence iteratively with the sentence itself from the previous iteration, and augment the semantics of the context representation from BERT with both entity pair and triggers skillfully. We conduct extensive experiments to evaluate the proposed model and effectively obtain empirical improvement in TACRED.
Fichier principal
Vignette du fichier
529309_1_En_11_Chapter.pdf (531.89 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04178754 , version 1 (08-08-2023)

Licence

Identifiers

Cite

En Li, Shumin Shi, Zhikun Yang, He Yan Huang. Augmenting Context Representation with Triggers Knowledge for Relation Extraction. 12th International Conference on Intelligent Information Processing (IIP), May 2022, Qingdao, China. pp.124-135, ⟨10.1007/978-3-031-03948-5_11⟩. ⟨hal-04178754⟩
27 View
3 Download

Altmetric

Share

More