@inproceedings{hayashibe-mitsuzawa-2020-sentence,
title = "Sentence Boundary Detection on Line Breaks in {J}apanese",
author = "Hayashibe, Yuta and
Mitsuzawa, Kensuke",
editor = "Xu, Wei and
Ritter, Alan and
Baldwin, Tim and
Rahimi, Afshin",
booktitle = "Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wnut-1.10",
doi = "10.18653/v1/2020.wnut-1.10",
pages = "71--75",
abstract = "For NLP, sentence boundary detection (SBD) is an essential task to decompose a text into sentences. Most of the previous studies have used a simple rule that uses only typical characters as sentence boundaries. However, some characters may or may not be sentence boundaries depending on the context. We focused on line breaks in them. We newly constructed annotated corpora, implemented sentence boundary detectors, and analyzed performance of SBD in several settings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hayashibe-mitsuzawa-2020-sentence">
<titleInfo>
<title>Sentence Boundary Detection on Line Breaks in Japanese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuta</namePart>
<namePart type="family">Hayashibe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kensuke</namePart>
<namePart type="family">Mitsuzawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)</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>For NLP, sentence boundary detection (SBD) is an essential task to decompose a text into sentences. Most of the previous studies have used a simple rule that uses only typical characters as sentence boundaries. However, some characters may or may not be sentence boundaries depending on the context. We focused on line breaks in them. We newly constructed annotated corpora, implemented sentence boundary detectors, and analyzed performance of SBD in several settings.</abstract>
<identifier type="citekey">hayashibe-mitsuzawa-2020-sentence</identifier>
<identifier type="doi">10.18653/v1/2020.wnut-1.10</identifier>
<location>
<url>https://aclanthology.org/2020.wnut-1.10</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>71</start>
<end>75</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sentence Boundary Detection on Line Breaks in Japanese
%A Hayashibe, Yuta
%A Mitsuzawa, Kensuke
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%Y Rahimi, Afshin
%S Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F hayashibe-mitsuzawa-2020-sentence
%X For NLP, sentence boundary detection (SBD) is an essential task to decompose a text into sentences. Most of the previous studies have used a simple rule that uses only typical characters as sentence boundaries. However, some characters may or may not be sentence boundaries depending on the context. We focused on line breaks in them. We newly constructed annotated corpora, implemented sentence boundary detectors, and analyzed performance of SBD in several settings.
%R 10.18653/v1/2020.wnut-1.10
%U https://aclanthology.org/2020.wnut-1.10
%U https://doi.org/10.18653/v1/2020.wnut-1.10
%P 71-75
Markdown (Informal)
[Sentence Boundary Detection on Line Breaks in Japanese](https://aclanthology.org/2020.wnut-1.10) (Hayashibe & Mitsuzawa, WNUT 2020)
ACL