@inproceedings{cho-etal-2019-paraphrase,
title = "Paraphrase Generation for Semi-Supervised Learning in {NLU}",
author = "Cho, Eunah and
Xie, He and
Campbell, William M.",
editor = "Bosselut, Antoine and
Celikyilmaz, Asli and
Ghazvininejad, Marjan and
Iyer, Srinivasan and
Khandelwal, Urvashi and
Rashkin, Hannah and
Wolf, Thomas",
booktitle = "Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-2306",
doi = "10.18653/v1/W19-2306",
pages = "45--54",
abstract = "Semi-supervised learning is an efficient way to improve performance for natural language processing systems. In this work, we propose Para-SSL, a scheme to generate candidate utterances using paraphrasing and methods from semi-supervised learning. In order to perform paraphrase generation in the context of a dialog system, we automatically extract paraphrase pairs to create a paraphrase corpus. Using this data, we build a paraphrase generation system and perform one-to-many generation, followed by a validation step to select only the utterances with good quality. The paraphrase-based semi-supervised learning is applied to five functionalities in a natural language understanding system. Our proposed method for semi-supervised learning using paraphrase generation does not require user utterances and can be applied prior to releasing a new functionality to a system. Experiments show that we can achieve up to 19{\%} of relative slot error reduction without an access to user utterances, and up to 35{\%} when leveraging live traffic utterances.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cho-etal-2019-paraphrase">
<titleInfo>
<title>Paraphrase Generation for Semi-Supervised Learning in NLU</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eunah</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">He</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Campbell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Bosselut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asli</namePart>
<namePart type="family">Celikyilmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marjan</namePart>
<namePart type="family">Ghazvininejad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Srinivasan</namePart>
<namePart type="family">Iyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Urvashi</namePart>
<namePart type="family">Khandelwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hannah</namePart>
<namePart type="family">Rashkin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Wolf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Semi-supervised learning is an efficient way to improve performance for natural language processing systems. In this work, we propose Para-SSL, a scheme to generate candidate utterances using paraphrasing and methods from semi-supervised learning. In order to perform paraphrase generation in the context of a dialog system, we automatically extract paraphrase pairs to create a paraphrase corpus. Using this data, we build a paraphrase generation system and perform one-to-many generation, followed by a validation step to select only the utterances with good quality. The paraphrase-based semi-supervised learning is applied to five functionalities in a natural language understanding system. Our proposed method for semi-supervised learning using paraphrase generation does not require user utterances and can be applied prior to releasing a new functionality to a system. Experiments show that we can achieve up to 19% of relative slot error reduction without an access to user utterances, and up to 35% when leveraging live traffic utterances.</abstract>
<identifier type="citekey">cho-etal-2019-paraphrase</identifier>
<identifier type="doi">10.18653/v1/W19-2306</identifier>
<location>
<url>https://aclanthology.org/W19-2306</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>45</start>
<end>54</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Paraphrase Generation for Semi-Supervised Learning in NLU
%A Cho, Eunah
%A Xie, He
%A Campbell, William M.
%Y Bosselut, Antoine
%Y Celikyilmaz, Asli
%Y Ghazvininejad, Marjan
%Y Iyer, Srinivasan
%Y Khandelwal, Urvashi
%Y Rashkin, Hannah
%Y Wolf, Thomas
%S Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F cho-etal-2019-paraphrase
%X Semi-supervised learning is an efficient way to improve performance for natural language processing systems. In this work, we propose Para-SSL, a scheme to generate candidate utterances using paraphrasing and methods from semi-supervised learning. In order to perform paraphrase generation in the context of a dialog system, we automatically extract paraphrase pairs to create a paraphrase corpus. Using this data, we build a paraphrase generation system and perform one-to-many generation, followed by a validation step to select only the utterances with good quality. The paraphrase-based semi-supervised learning is applied to five functionalities in a natural language understanding system. Our proposed method for semi-supervised learning using paraphrase generation does not require user utterances and can be applied prior to releasing a new functionality to a system. Experiments show that we can achieve up to 19% of relative slot error reduction without an access to user utterances, and up to 35% when leveraging live traffic utterances.
%R 10.18653/v1/W19-2306
%U https://aclanthology.org/W19-2306
%U https://doi.org/10.18653/v1/W19-2306
%P 45-54
Markdown (Informal)
[Paraphrase Generation for Semi-Supervised Learning in NLU](https://aclanthology.org/W19-2306) (Cho et al., NAACL 2019)
ACL
- Eunah Cho, He Xie, and William M. Campbell. 2019. Paraphrase Generation for Semi-Supervised Learning in NLU. In Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation, pages 45–54, Minneapolis, Minnesota. Association for Computational Linguistics.