@inproceedings{higashiyama-etal-2021-user,
title = "User-Generated Text Corpus for Evaluating {J}apanese Morphological Analysis and Lexical Normalization",
author = "Higashiyama, Shohei and
Utiyama, Masao and
Watanabe, Taro and
Sumita, Eiichiro",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.438",
doi = "10.18653/v1/2021.naacl-main.438",
pages = "5532--5541",
abstract = "Morphological analysis (MA) and lexical normalization (LN) are both important tasks for Japanese user-generated text (UGT). To evaluate and compare different MA/LN systems, we have constructed a publicly available Japanese UGT corpus. Our corpus comprises 929 sentences annotated with morphological and normalization information, along with category information we classified for frequent UGT-specific phenomena. Experiments on the corpus demonstrated the low performance of existing MA/LN methods for non-general words and non-standard forms, indicating that the corpus would be a challenging benchmark for further research on UGT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="higashiyama-etal-2021-user">
<titleInfo>
<title>User-Generated Text Corpus for Evaluating Japanese Morphological Analysis 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>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Morphological analysis (MA) and lexical normalization (LN) are both important tasks for Japanese user-generated text (UGT). To evaluate and compare different MA/LN systems, we have constructed a publicly available Japanese UGT corpus. Our corpus comprises 929 sentences annotated with morphological and normalization information, along with category information we classified for frequent UGT-specific phenomena. Experiments on the corpus demonstrated the low performance of existing MA/LN methods for non-general words and non-standard forms, indicating that the corpus would be a challenging benchmark for further research on UGT.</abstract>
<identifier type="citekey">higashiyama-etal-2021-user</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.438</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.438</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>5532</start>
<end>5541</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T User-Generated Text Corpus for Evaluating Japanese Morphological Analysis and Lexical Normalization
%A Higashiyama, Shohei
%A Utiyama, Masao
%A Watanabe, Taro
%A Sumita, Eiichiro
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F higashiyama-etal-2021-user
%X Morphological analysis (MA) and lexical normalization (LN) are both important tasks for Japanese user-generated text (UGT). To evaluate and compare different MA/LN systems, we have constructed a publicly available Japanese UGT corpus. Our corpus comprises 929 sentences annotated with morphological and normalization information, along with category information we classified for frequent UGT-specific phenomena. Experiments on the corpus demonstrated the low performance of existing MA/LN methods for non-general words and non-standard forms, indicating that the corpus would be a challenging benchmark for further research on UGT.
%R 10.18653/v1/2021.naacl-main.438
%U https://aclanthology.org/2021.naacl-main.438
%U https://doi.org/10.18653/v1/2021.naacl-main.438
%P 5532-5541
Markdown (Informal)
[User-Generated Text Corpus for Evaluating Japanese Morphological Analysis and Lexical Normalization](https://aclanthology.org/2021.naacl-main.438) (Higashiyama et al., NAACL 2021)
ACL