@inproceedings{xu-etal-2021-augnlg,
title = "{A}ug{NLG}: Few-shot Natural Language Generation using Self-trained Data Augmentation",
author = "Xu, Xinnuo and
Wang, Guoyin and
Kim, Young-Bum and
Lee, Sungjin",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.95",
doi = "10.18653/v1/2021.acl-long.95",
pages = "1183--1195",
abstract = "Natural Language Generation (NLG) is a key component in a task-oriented dialogue system, which converts the structured meaning representation (MR) to the natural language. For large-scale conversational systems, where it is common to have over hundreds of intents and thousands of slots, neither template-based approaches nor model-based approaches are scalable. Recently, neural NLGs started leveraging transfer learning and showed promising results in few-shot settings. This paper proposes AugNLG, a novel data augmentation approach that combines a self-trained neural retrieval model with a few-shot learned NLU model, to automatically create MR-to-Text data from open-domain texts. The proposed system mostly outperforms the state-of-the-art methods on the FewshotWOZ data in both BLEU and Slot Error Rate. We further confirm improved results on the FewshotSGD data and provide comprehensive analysis results on key components of our system. Our code and data are available at \url{https://github.com/XinnuoXu/AugNLG}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2021-augnlg">
<titleInfo>
<title>AugNLG: Few-shot Natural Language Generation using Self-trained Data Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinnuo</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guoyin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Young-Bum</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sungjin</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Natural Language Generation (NLG) is a key component in a task-oriented dialogue system, which converts the structured meaning representation (MR) to the natural language. For large-scale conversational systems, where it is common to have over hundreds of intents and thousands of slots, neither template-based approaches nor model-based approaches are scalable. Recently, neural NLGs started leveraging transfer learning and showed promising results in few-shot settings. This paper proposes AugNLG, a novel data augmentation approach that combines a self-trained neural retrieval model with a few-shot learned NLU model, to automatically create MR-to-Text data from open-domain texts. The proposed system mostly outperforms the state-of-the-art methods on the FewshotWOZ data in both BLEU and Slot Error Rate. We further confirm improved results on the FewshotSGD data and provide comprehensive analysis results on key components of our system. Our code and data are available at https://github.com/XinnuoXu/AugNLG.</abstract>
<identifier type="citekey">xu-etal-2021-augnlg</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.95</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.95</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>1183</start>
<end>1195</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AugNLG: Few-shot Natural Language Generation using Self-trained Data Augmentation
%A Xu, Xinnuo
%A Wang, Guoyin
%A Kim, Young-Bum
%A Lee, Sungjin
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F xu-etal-2021-augnlg
%X Natural Language Generation (NLG) is a key component in a task-oriented dialogue system, which converts the structured meaning representation (MR) to the natural language. For large-scale conversational systems, where it is common to have over hundreds of intents and thousands of slots, neither template-based approaches nor model-based approaches are scalable. Recently, neural NLGs started leveraging transfer learning and showed promising results in few-shot settings. This paper proposes AugNLG, a novel data augmentation approach that combines a self-trained neural retrieval model with a few-shot learned NLU model, to automatically create MR-to-Text data from open-domain texts. The proposed system mostly outperforms the state-of-the-art methods on the FewshotWOZ data in both BLEU and Slot Error Rate. We further confirm improved results on the FewshotSGD data and provide comprehensive analysis results on key components of our system. Our code and data are available at https://github.com/XinnuoXu/AugNLG.
%R 10.18653/v1/2021.acl-long.95
%U https://aclanthology.org/2021.acl-long.95
%U https://doi.org/10.18653/v1/2021.acl-long.95
%P 1183-1195
Markdown (Informal)
[AugNLG: Few-shot Natural Language Generation using Self-trained Data Augmentation](https://aclanthology.org/2021.acl-long.95) (Xu et al., ACL-IJCNLP 2021)
ACL