Timezone: »

 
Poster
Teacher Forcing Recovers Reward Functions for Text Generation
Yongchang Hao · Yuxin Liu · Lili Mou

Tue Nov 29 02:00 PM -- 04:00 PM (PST) @ Hall J #339
in Poster Session 2 »

Reinforcement learning (RL) has been widely used in text generation to alleviate the exposure bias issue or to utilize non-parallel datasets. The reward function plays an important role in making RL training successful. However, previous reward functions are typically task-specific and sparse, restricting the use of RL. In our work, we propose a task-agnostic approach that derives a step-wise reward function directly from a model trained with teacher forcing. We additionally propose a simple modification to stabilize the RL training on non-parallel datasets with our induced reward function. Empirical results show that our method outperforms self-training and reward regression methods on several text generation tasks, confirming the effectiveness of our reward function.

Keywords: Natural Language Processing · Reinforcement Learning · Text generation
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Yongchang Hao (University of Alberta)
Yuxin Liu (University of Alberta)
Lili Mou (University of Alberta)

More from the Same Authors