Natural Language Generation as Planning under Uncertainty Using Reinforcement Learning
This work addresses natural language generation for spoken dialogue systems, offering an incremental improvement over existing methods by incorporating reinforcement learning with noisy feedback.
The paper tackles the problem of generating natural language in spoken dialogue systems by developing a reinforcement learning model that adapts to noisy feedback from the generation context. The learned policy significantly outperforms prior approaches in presenting search results to users, balancing utterance length, information conveyed, and cognitive load.
We present and evaluate a new model for Natural Language Generation (NLG) in Spoken Dialogue Systems, based on statistical planning, given noisy feedback from the current generation context (e.g. a user and a surface realiser). We study its use in a standard NLG problem: how to present information (in this case a set of search results) to users, given the complex trade- offs between utterance length, amount of information conveyed, and cognitive load. We set these trade-offs by analysing existing MATCH data. We then train a NLG pol- icy using Reinforcement Learning (RL), which adapts its behaviour to noisy feed- back from the current generation context. This policy is compared to several base- lines derived from previous work in this area. The learned policy significantly out- performs all the prior approaches.