@inproceedings{higashiyama-etal-2021-text,
title = "A Text Editing Approach to Joint {J}apanese Word Segmentation, {POS} Tagging, and Lexical Normalization",
author = "Higashiyama, Shohei and
Utiyama, Masao and
Watanabe, Taro and
Sumita, Eiichiro",
editor = "Xu, Wei and
Ritter, Alan and
Baldwin, Tim and
Rahimi, Afshin",
booktitle = "Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)",
month = nov,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wnut-1.9/",
doi = "10.18653/v1/2021.wnut-1.9",
pages = "67--80",
abstract = "Lexical normalization, in addition to word segmentation and part-of-speech tagging, is a fundamental task for Japanese user-generated text processing. In this paper, we propose a text editing model to solve the three task jointly and methods of pseudo-labeled data generation to overcome the problem of data deficiency. Our experiments showed that the proposed model achieved better normalization performance when trained on more diverse pseudo-labeled data."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="higashiyama-etal-2021-text">
<titleInfo>
<title>A Text Editing Approach to Joint Japanese Word Segmentation, POS Tagging, and Lexical Normalization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shohei</namePart>
<namePart type="family">Higashiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eiichiro</namePart>
<namePart type="family">Sumita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afshin</namePart>
<namePart type="family">Rahimi</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>Lexical normalization, in addition to word segmentation and part-of-speech tagging, is a fundamental task for Japanese user-generated text processing. In this paper, we propose a text editing model to solve the three task jointly and methods of pseudo-labeled data generation to overcome the problem of data deficiency. Our experiments showed that the proposed model achieved better normalization performance when trained on more diverse pseudo-labeled data.</abstract>
<identifier type="citekey">higashiyama-etal-2021-text</identifier>
<identifier type="doi">10.18653/v1/2021.wnut-1.9</identifier>
<location>
<url>https://aclanthology.org/2021.wnut-1.9/</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>67</start>
<end>80</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Text Editing Approach to Joint Japanese Word Segmentation, POS Tagging, and Lexical Normalization
%A Higashiyama, Shohei
%A Utiyama, Masao
%A Watanabe, Taro
%A Sumita, Eiichiro
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%Y Rahimi, Afshin
%S Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online
%F higashiyama-etal-2021-text
%X Lexical normalization, in addition to word segmentation and part-of-speech tagging, is a fundamental task for Japanese user-generated text processing. In this paper, we propose a text editing model to solve the three task jointly and methods of pseudo-labeled data generation to overcome the problem of data deficiency. Our experiments showed that the proposed model achieved better normalization performance when trained on more diverse pseudo-labeled data.
%R 10.18653/v1/2021.wnut-1.9
%U https://aclanthology.org/2021.wnut-1.9/
%U https://doi.org/10.18653/v1/2021.wnut-1.9
%P 67-80
Markdown (Informal)
[A Text Editing Approach to Joint Japanese Word Segmentation, POS Tagging, and Lexical Normalization](https://aclanthology.org/2021.wnut-1.9/) (Higashiyama et al., WNUT 2021)
ACL