How Helpful is Inverse Reinforcement Learning for Table-to-Text Generation?

Sayan Ghosh, Zheng Qi, Snigdha Chaturvedi, Shashank Srivastava

Abstract:

Existing approaches for the Table-to-Text task
suffer from issues such as missing information,
hallucination and repetition. Many approaches
to this problem use Reinforcement Learning
(RL), which maximizes a single manually defined reward, such as BLEU. In this work, we
instead pose the Table-to-Text task as Inverse
Reinforcement Learning (IRL) problem. We
explore using multiple interpretable unsupervised reward components that are combined
linearly to form a composite reward function.
The composite reward function and the description generator are learned jointly. We
find that IRL outperforms strong RL baselines
marginally. We further study the generalization of learned IRL rewards in scenarios involving domain adaptation. Our experiments
reveal significant challenges in using IRL for
this task.