@inproceedings{zheng-etal-2018-correct,
title = "How do you correct run-on sentences it{'}s not as easy as it seems",
author = "Zheng, Junchao and
Napoles, Courtney and
Tetreault, Joel and
Omelianchuk, Kostiantyn",
editor = "Xu, Wei and
Ritter, Alan and
Baldwin, Tim and
Rahimi, Afshin",
booktitle = "Proceedings of the 2018 {EMNLP} Workshop W-{NUT}: The 4th Workshop on Noisy User-generated Text",
month = nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-6105",
doi = "10.18653/v1/W18-6105",
pages = "33--38",
abstract = "Run-on sentences are common grammatical mistakes but little research has tackled this problem to date. This work introduces two machine learning models to correct run-on sentences that outperform leading methods for related tasks, punctuation restoration and whole-sentence grammatical error correction. Due to the limited annotated data for this error, we experiment with artificially generating training data from clean newswire text. Our findings suggest artificial training data is viable for this task. We discuss implications for correcting run-ons and other types of mistakes that have low coverage in error-annotated corpora.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-etal-2018-correct">
<titleInfo>
<title>How do you correct run-on sentences it’s not as easy as it seems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junchao</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Courtney</namePart>
<namePart type="family">Napoles</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kostiantyn</namePart>
<namePart type="family">Omelianchuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text</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">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Run-on sentences are common grammatical mistakes but little research has tackled this problem to date. This work introduces two machine learning models to correct run-on sentences that outperform leading methods for related tasks, punctuation restoration and whole-sentence grammatical error correction. Due to the limited annotated data for this error, we experiment with artificially generating training data from clean newswire text. Our findings suggest artificial training data is viable for this task. We discuss implications for correcting run-ons and other types of mistakes that have low coverage in error-annotated corpora.</abstract>
<identifier type="citekey">zheng-etal-2018-correct</identifier>
<identifier type="doi">10.18653/v1/W18-6105</identifier>
<location>
<url>https://aclanthology.org/W18-6105</url>
</location>
<part>
<date>2018-11</date>
<extent unit="page">
<start>33</start>
<end>38</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How do you correct run-on sentences it’s not as easy as it seems
%A Zheng, Junchao
%A Napoles, Courtney
%A Tetreault, Joel
%A Omelianchuk, Kostiantyn
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%Y Rahimi, Afshin
%S Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text
%D 2018
%8 November
%I Association for Computational Linguistics
%C Brussels, Belgium
%F zheng-etal-2018-correct
%X Run-on sentences are common grammatical mistakes but little research has tackled this problem to date. This work introduces two machine learning models to correct run-on sentences that outperform leading methods for related tasks, punctuation restoration and whole-sentence grammatical error correction. Due to the limited annotated data for this error, we experiment with artificially generating training data from clean newswire text. Our findings suggest artificial training data is viable for this task. We discuss implications for correcting run-ons and other types of mistakes that have low coverage in error-annotated corpora.
%R 10.18653/v1/W18-6105
%U https://aclanthology.org/W18-6105
%U https://doi.org/10.18653/v1/W18-6105
%P 33-38
Markdown (Informal)
[How do you correct run-on sentences it’s not as easy as it seems](https://aclanthology.org/W18-6105) (Zheng et al., WNUT 2018)
ACL