Paper Info
Title
Joint On-Line Learning Of A Zero-Shot Spoken Semantic Parser And A Reinforcement Learning Dialogue Manager
Abstract
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 prerecorded 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.
Year
DOI
Venue
2018
10.1109/icassp.2019.8683274
2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
Keywords
Field
DocType
on-line learning, adversarial bandit, reinforcement learning, zero-shot learning, spoken dialogue systems
Data collection,Bottleneck,Off the shelf,Dialogue management,Annotation,Computer science,Natural language processing,Artificial intelligence,Parsing,Spoken language,Reinforcement learning
Journal
Volume
ISSN
Citations 
abs/1810.00924
1520-6149
0
PageRank 
References 
Authors
0.34
0
4
Name
Order
Citations
PageRank
Matthieu Riou102.03
Bassam Jabaian2287.00
Stéphane Huet3409.15
Fabrice Lefèvre418526.62