Dialogue Policy Learning for Combinations of Noise and User Simulation: Transfer Results
Oliver Lemon, Xingkun Liu · 2007
Once a dialogue strategy has been learned for a particular set of conditions, we need to know how well it will perform when deployed in different conditions to those it was specifically trained for, i.e. how robust it is in transfer to different conditions.We first present novel learning results for different ASR noise models combined with different user simulations.We then show that policies trained in high-noise conditions perform significantly better than those trained for lownoise conditions, even when deployed in low-noise environments.