@inproceedings{tran-nguyen-2018-dual,
title = "Dual Latent Variable Model for Low-Resource Natural Language Generation in Dialogue Systems",
author = "Tran, Van-Khanh and
Nguyen, Le-Minh",
editor = "Korhonen, Anna and
Titov, Ivan",
booktitle = "Proceedings of the 22nd Conference on Computational Natural Language Learning",
month = oct,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/K18-1003",
doi = "10.18653/v1/K18-1003",
pages = "21--30",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tran-nguyen-2018-dual">
<titleInfo>
<title>Dual Latent Variable Model for Low-Resource Natural Language Generation in Dialogue Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Van-Khanh</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Le-Minh</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Conference on Computational Natural Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Titov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">tran-nguyen-2018-dual</identifier>
<identifier type="doi">10.18653/v1/K18-1003</identifier>
<location>
<url>https://aclanthology.org/K18-1003</url>
</location>
<part>
<date>2018-10</date>
<extent unit="page">
<start>21</start>
<end>30</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dual Latent Variable Model for Low-Resource Natural Language Generation in Dialogue Systems
%A Tran, Van-Khanh
%A Nguyen, Le-Minh
%Y Korhonen, Anna
%Y Titov, Ivan
%S Proceedings of the 22nd Conference on Computational Natural Language Learning
%D 2018
%8 October
%I Association for Computational Linguistics
%C Brussels, Belgium
%F tran-nguyen-2018-dual
%X 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.
%R 10.18653/v1/K18-1003
%U https://aclanthology.org/K18-1003
%U https://doi.org/10.18653/v1/K18-1003
%P 21-30
Markdown (Informal)
[Dual Latent Variable Model for Low-Resource Natural Language Generation in Dialogue Systems](https://aclanthology.org/K18-1003) (Tran & Nguyen, CoNLL 2018)
ACL