Dual latent variable model for low-resource natural language generation in dialogue systems
conference contribution
posted on 2018-01-01, 00:00authored byVan Khanh Tran, Le-Minh Nguyen
Recent deep learning models have shown improving results to natural language generation (NLG) irrespective of providing sufficient annotated data. However, a modest training data may harm such models’ performance. Thus, how to build a generator that can utilize as much of knowledge from a low-resource setting data is a crucial issue in NLG. This paper presents a variational neural-based generation model to tackle the NLG problem of having limited labeled dataset, in which we integrate a variational inference into an encoder-decoder generator and introduce a novel auxiliary auto-encoding with an effective training procedure. Experiments showed that the proposed methods not only outperform the previous models when having sufficient training dataset but also demonstrate strong ability to work acceptably well when the training data is scarce.
History
Pagination
21-30
Location
Brussels, Belgium
Start date
2018-10-31
End date
2018-11-01
ISBN-13
978-1-948087-72-8
Language
eng
Publication classification
E1.1 Full written paper - refereed
Copyright notice
2018, Association for Computational Linguistics
Editor/Contributor(s)
[Unknown]
Title of proceedings
CoNLL 2018 : Proceedings of the 22nd Conference on Computational Natural Language Learning
Event
Association for Computational Linguistics. Conference (22nd : 2018 : Brussels, Belgium)
Publisher
Association for Computational Linguistics
Place of publication
Stroudsburg, Pa.
Series
Association for Computational Linguistics Conference