Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                

Dual Latent Variable Model for Low-Resource Natural Language Generation in Dialogue Systems

Van-Khanh Tran, Le-Minh Nguyen


Abstract
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.
Anthology ID:
K18-1003
Volume:
Proceedings of the 22nd Conference on Computational Natural Language Learning
Month:
October
Year:
2018
Address:
Brussels, Belgium
Editors:
Anna Korhonen, Ivan Titov
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
21–30
Language:
URL:
https://aclanthology.org/K18-1003
DOI:
10.18653/v1/K18-1003
Bibkey:
Cite (ACL):
Van-Khanh Tran and Le-Minh Nguyen. 2018. Dual Latent Variable Model for Low-Resource Natural Language Generation in Dialogue Systems. In Proceedings of the 22nd Conference on Computational Natural Language Learning, pages 21–30, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Dual Latent Variable Model for Low-Resource Natural Language Generation in Dialogue Systems (Tran & Nguyen, CoNLL 2018)
Copy Citation:
PDF:
https://aclanthology.org/K18-1003.pdf