Learning from Real Users: Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems: Paper and Code

Get our free extension to see links to code for papers anywhere online!Free add-on: code for papers everywhere!Free add-on: See code for papers anywhere!

Add to Chrome

Add to Firefox

Add to Edge

Learning from Real Users: Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems

Aug 13, 2015

Pei-Hao Su, David Vandyke, Milica Gasic, Dongho Kim, Nikola Mrksic, Tsung-Hsien Wen, Steve Young

Figure 1 for Learning from Real Users: Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems

Figure 2 for Learning from Real Users: Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems

Figure 3 for Learning from Real Users: Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems

Figure 4 for Learning from Real Users: Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems

Share this with someone who'll enjoy it:

To train a statistical spoken dialogue system (SDS) it is essential that an accurate method for measuring task success is available. To date training has relied on presenting a task to either simulated or paid users and inferring the dialogue's success by observing whether this presented task was achieved or not. Our aim however is to be able to learn from real users acting under their own volition, in which case it is non-trivial to rate the success as any prior knowledge of the task is simply unavailable. User feedback may be utilised but has been found to be inconsistent. Hence, here we present two neural network models that evaluate a sequence of turn-level features to rate the success of a dialogue. Importantly these models make no use of any prior knowledge of the user's task. The models are trained on dialogues generated by a simulated user and the best model is then used to train a policy on-line which is shown to perform at least as well as a baseline system using prior knowledge of the user's task. We note that the models should also be of interest for evaluating SDS and for monitoring a dialogue in rule-based SDS.

* Accepted for publication in INTERSPEECH 2015

View paper on

Share this with someone who'll enjoy it: