Event Extraction with Generative Adversarial Imitation Learning
This addresses event extraction for natural language processing by improving accuracy over existing methods, though it is incremental as it adapts known techniques to a specific task.
The paper tackles event extraction by using a generative adversarial imitation learning framework to estimate dynamic rewards based on expert actions, outperforming state-of-the-art methods without feature engineering.
We propose a new method for event extraction (EE) task based on an imitation learning framework, specifically, inverse reinforcement learning (IRL) via generative adversarial network (GAN). The GAN estimates proper rewards according to the difference between the actions committed by the expert (or ground truth) and the agent among complicated states in the environment. EE task benefits from these dynamic rewards because instances and labels yield to various extents of difficulty and the gains are expected to be diverse -- e.g., an ambiguous but correctly detected trigger or argument should receive high gains -- while the traditional RL models usually neglect such differences and pay equal attention on all instances. Moreover, our experiments also demonstrate that the proposed framework outperforms state-of-the-art methods, without explicit feature engineering.