Sorry, you need to enable JavaScript to visit this website.

Joint On-line Learning of a Zero-Shot Spoken Semantic Parser and a Reinforcement Learning Dialogue Manager

Citation Author(s):
Matthieu Riou, Bassam Jabaian, Stéphane Huet, Fabrice Lefèvre
Submitted by:
Matthieu Riou
Last updated:
10 May 2019 - 5:56pm
Document Type:
Poster
Document Year:
2019
Event:
Presenters:
Matthieu Riou
Paper Code:
P3478
 

Despite many recent advances for the design of dialogue systems, a true bottleneck remains the acquisition of data required to train its components. Unlike many other language processing applications, dialogue systems require interactions with users, therefore it is complex to develop them with pre-recorded data. Building on previous works, on-line learning is pursued here as a most convenient way to address the issue. Data collection, annotation and use in learning algorithms are performed in a single process. The main difficulties are then: to bootstrap an initial basic system, and to control the level of additional cost on the user side. Considering that well-performing solutions can be used directly off the shelf for speech recognition and synthesis, the study is focused on learning the spoken language understanding and dialogue management modules only. Several variants of joint learning are investigated and tested with user trials to confirm that the overall on-line learning can be obtained after only a few hundred training dialogues and can overstep an expert-based system.

Paper link : https://ieeexplore.ieee.org/document/8683274

up
0 users have voted: