Open Access

ARTICLE

Joint Self-Attention Based Neural Networks for Semantic Relation Extraction

Jun Sun¹, Yan Li¹, Yatian Shen^1,*, Wenke Ding¹, Xianjin Shi¹, Lei Zhang¹, Xiajiong Shen¹, Jing He²
1 School of Computer and Information Engineering, Henan University, Kaifeng, 475000, China.
2 The Corporate and Investment, Bank Technology, J. P. Morgan Chase N. A. 25 Bank St, Canary Wharf, London, E145JP, United Kingdom.
*Corresponding Author: Yatian Shen. Email: .

Journal of Information Hiding and Privacy Protection 2019, 1(2), 69-75. https://doi.org/10.32604/jihpp.2019.06357

Abstract

Relation extraction is an important task in NLP community. However, some models often fail in capturing Long-distance dependence on semantics, and the interaction between semantics of two entities is ignored. In this paper, we propose a novel neural network model for semantic relation classification called joint self-attention bi-LSTM (SA-Bi-LSTM) to model the internal structure of the sentence to obtain the importance of each word of the sentence without relying on additional information, and capture Long-distance dependence on semantics. We conduct experiments using the SemEval-2010 Task 8 dataset. Extensive experiments and the results demonstrated that the proposed method is effective against relation classification, which can obtain state-of-the-art classification accuracy just with minimal feature engineering.

---

Keywords

Self-attention, relation extraction, neural networks.

---

Citations