Joint entity and event extraction with generative adversarial imitation learning

Tongtao Zhang, Heng Ji, Avirup Sil

Research output: Contribution to journalArticlepeer-review


We propose a new framework for entity and event extraction based on generative adversarial imitation learning—an inverse reinforcement learning method using a generative adversarial network (GAN). We assume that instances and labels yield to various extents of difficulty and the gains and penalties (rewards) are expected to be diverse. We utilize discriminators to estimate proper rewards according to the difference between the labels committed by the ground-truth (expert) and the extractor (agent). Our experiments demonstrate that the proposed framework outperforms state-of-the-art methods.

Original languageEnglish (US)
Pages (from-to)99-120
Number of pages22
JournalData Intelligence
Issue number2
StatePublished - Apr 1 2019
Externally publishedYes


  • Event extraction
  • Generative adversarial network
  • Imitation learning
  • Information extraction

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Information Systems
  • Library and Information Sciences


Dive into the research topics of 'Joint entity and event extraction with generative adversarial imitation learning'. Together they form a unique fingerprint.

Cite this