TY - JOUR
T1 - Causality Extraction With GAN
AU - Feng, Chong
AU - Kang, Li Qi
AU - Shi, Ge
AU - Huang, He Yan
N1 - Publisher Copyright:
Copyright © 2018 Acta Automatica Sinica. All rights reserved.
PY - 2018/5/1
Y1 - 2018/5/1
N2 - Causality extraction is of important practical value in tasks such as event prediction, scenario generation, question answering, and textual implication; but most of the existing causality extraction methods require artificial definition of patterns and constraints and are heavily dependent on knowledge base. In this paper, the bidirectional gated recurrent units networks (BGRU) with attention mechanism are merged with confrontational learning by leveraging the confrontational learning characteristics of generative adversarial networks (GAN). Through redefining the generator and discriminator, the basic causality extraction network can construct a confrontation with the discriminator, and then obtain a high distinguishing feature from the causality interpretation information. Our experiments show that our approach leads to an improved performance over strong baselines.
AB - Causality extraction is of important practical value in tasks such as event prediction, scenario generation, question answering, and textual implication; but most of the existing causality extraction methods require artificial definition of patterns and constraints and are heavily dependent on knowledge base. In this paper, the bidirectional gated recurrent units networks (BGRU) with attention mechanism are merged with confrontational learning by leveraging the confrontational learning characteristics of generative adversarial networks (GAN). Through redefining the generator and discriminator, the basic causality extraction network can construct a confrontation with the discriminator, and then obtain a high distinguishing feature from the causality interpretation information. Our experiments show that our approach leads to an improved performance over strong baselines.
KW - Adversarial learning
KW - Attention mechanism
KW - Causality extraction
KW - Generative adversarial network (GAN)
UR - http://www.scopus.com/inward/record.url?scp=85049559610&partnerID=8YFLogxK
U2 - 10.16383/j.aas.2018.c170481
DO - 10.16383/j.aas.2018.c170481
M3 - Article
AN - SCOPUS:85049559610
SN - 0254-4156
VL - 44
SP - 811
EP - 818
JO - Zidonghua Xuebao/Acta Automatica Sinica
JF - Zidonghua Xuebao/Acta Automatica Sinica
IS - 5
ER -