Neural Text Generation with Artificial Negative Examples

Understand

Neural text generation models conditioning on given input (e.g.

• machine translation and image captioning) are usually trained by maximum likelihood estimation of target text.
• However, the trained models suffer from various types of errors at inference time.
• In this paper, we propose to suppress an arbitrary type of errors by training the text generation model in a reinforcement learning framework, where we use a trainable reward function that is capable of discriminating between references and sentences containing the targeted type of errors.