@inproceedings{saito-etal-2017-improving,
title = "Improving Neural Text Normalization with Data Augmentation at Character- and Morphological Levels",
author = "Saito, Itsumi and
Suzuki, Jun and
Nishida, Kyosuke and
Sadamitsu, Kugatsu and
Kobashikawa, Satoshi and
Masumura, Ryo and
Matsumoto, Yuji and
Tomita, Junji",
editor = "Kondrak, Greg and
Watanabe, Taro",
booktitle = "Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = nov,
year = "2017",
address = "Taipei, Taiwan",
publisher = "Asian Federation of Natural Language Processing",
url = "https://aclanthology.org/I17-2044",
pages = "257--262",
abstract = "In this study, we investigated the effectiveness of augmented data for encoder-decoder-based neural normalization models. Attention based encoder-decoder models are greatly effective in generating many natural languages. {\%} such as machine translation or machine summarization. In general, we have to prepare for a large amount of training data to train an encoder-decoder model. Unlike machine translation, there are few training data for text-normalization tasks. In this paper, we propose two methods for generating augmented data. The experimental results with Japanese dialect normalization indicate that our methods are effective for an encoder-decoder model and achieve higher BLEU score than that of baselines. We also investigated the oracle performance and revealed that there is sufficient room for improving an encoder-decoder model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saito-etal-2017-improving">
<titleInfo>
<title>Improving Neural Text Normalization with Data Augmentation at Character- and Morphological Levels</title>
</titleInfo>
<name type="personal">
<namePart type="given">Itsumi</namePart>
<namePart type="family">Saito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyosuke</namePart>
<namePart type="family">Nishida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kugatsu</namePart>
<namePart type="family">Sadamitsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satoshi</namePart>
<namePart type="family">Kobashikawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryo</namePart>
<namePart type="family">Masumura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Matsumoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junji</namePart>
<namePart type="family">Tomita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Kondrak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Asian Federation of Natural Language Processing</publisher>
<place>
<placeTerm type="text">Taipei, Taiwan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this study, we investigated the effectiveness of augmented data for encoder-decoder-based neural normalization models. Attention based encoder-decoder models are greatly effective in generating many natural languages. % such as machine translation or machine summarization. In general, we have to prepare for a large amount of training data to train an encoder-decoder model. Unlike machine translation, there are few training data for text-normalization tasks. In this paper, we propose two methods for generating augmented data. The experimental results with Japanese dialect normalization indicate that our methods are effective for an encoder-decoder model and achieve higher BLEU score than that of baselines. We also investigated the oracle performance and revealed that there is sufficient room for improving an encoder-decoder model.</abstract>
<identifier type="citekey">saito-etal-2017-improving</identifier>
<location>
<url>https://aclanthology.org/I17-2044</url>
</location>
<part>
<date>2017-11</date>
<extent unit="page">
<start>257</start>
<end>262</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Neural Text Normalization with Data Augmentation at Character- and Morphological Levels
%A Saito, Itsumi
%A Suzuki, Jun
%A Nishida, Kyosuke
%A Sadamitsu, Kugatsu
%A Kobashikawa, Satoshi
%A Masumura, Ryo
%A Matsumoto, Yuji
%A Tomita, Junji
%Y Kondrak, Greg
%Y Watanabe, Taro
%S Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2017
%8 November
%I Asian Federation of Natural Language Processing
%C Taipei, Taiwan
%F saito-etal-2017-improving
%X In this study, we investigated the effectiveness of augmented data for encoder-decoder-based neural normalization models. Attention based encoder-decoder models are greatly effective in generating many natural languages. % such as machine translation or machine summarization. In general, we have to prepare for a large amount of training data to train an encoder-decoder model. Unlike machine translation, there are few training data for text-normalization tasks. In this paper, we propose two methods for generating augmented data. The experimental results with Japanese dialect normalization indicate that our methods are effective for an encoder-decoder model and achieve higher BLEU score than that of baselines. We also investigated the oracle performance and revealed that there is sufficient room for improving an encoder-decoder model.
%U https://aclanthology.org/I17-2044
%P 257-262
Markdown (Informal)
[Improving Neural Text Normalization with Data Augmentation at Character- and Morphological Levels](https://aclanthology.org/I17-2044) (Saito et al., IJCNLP 2017)
ACL
- Itsumi Saito, Jun Suzuki, Kyosuke Nishida, Kugatsu Sadamitsu, Satoshi Kobashikawa, Ryo Masumura, Yuji Matsumoto, and Junji Tomita. 2017. Improving Neural Text Normalization with Data Augmentation at Character- and Morphological Levels. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 257–262, Taipei, Taiwan. Asian Federation of Natural Language Processing.