@inproceedings{qiu-park-2019-artificial,
title = "Artificial Error Generation with Fluency Filtering",
author = "Qiu, Mengyang and
Park, Jungyeul",
editor = "Yannakoudakis, Helen and
Kochmar, Ekaterina and
Leacock, Claudia and
Madnani, Nitin and
Pil{\'a}n, Ildik{\'o} and
Zesch, Torsten",
booktitle = "Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-4408",
doi = "10.18653/v1/W19-4408",
pages = "87--91",
abstract = "The quantity and quality of training data plays a crucial role in grammatical error correction (GEC). However, due to the fact that obtaining human-annotated GEC data is both time-consuming and expensive, several studies have focused on generating artificial error sentences to boost training data for grammatical error correction, and shown significantly better performance. The present study explores how fluency filtering can affect the quality of artificial errors. By comparing artificial data filtered by different levels of fluency, we find that artificial error sentences with low fluency can greatly facilitate error correction, while high fluency errors introduce more noise.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qiu-park-2019-artificial">
<titleInfo>
<title>Artificial Error Generation with Fluency Filtering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mengyang</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jungyeul</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">Yannakoudakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Leacock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitin</namePart>
<namePart type="family">Madnani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ildikó</namePart>
<namePart type="family">Pilán</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Torsten</namePart>
<namePart type="family">Zesch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The quantity and quality of training data plays a crucial role in grammatical error correction (GEC). However, due to the fact that obtaining human-annotated GEC data is both time-consuming and expensive, several studies have focused on generating artificial error sentences to boost training data for grammatical error correction, and shown significantly better performance. The present study explores how fluency filtering can affect the quality of artificial errors. By comparing artificial data filtered by different levels of fluency, we find that artificial error sentences with low fluency can greatly facilitate error correction, while high fluency errors introduce more noise.</abstract>
<identifier type="citekey">qiu-park-2019-artificial</identifier>
<identifier type="doi">10.18653/v1/W19-4408</identifier>
<location>
<url>https://aclanthology.org/W19-4408</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>87</start>
<end>91</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Artificial Error Generation with Fluency Filtering
%A Qiu, Mengyang
%A Park, Jungyeul
%Y Yannakoudakis, Helen
%Y Kochmar, Ekaterina
%Y Leacock, Claudia
%Y Madnani, Nitin
%Y Pilán, Ildikó
%Y Zesch, Torsten
%S Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F qiu-park-2019-artificial
%X The quantity and quality of training data plays a crucial role in grammatical error correction (GEC). However, due to the fact that obtaining human-annotated GEC data is both time-consuming and expensive, several studies have focused on generating artificial error sentences to boost training data for grammatical error correction, and shown significantly better performance. The present study explores how fluency filtering can affect the quality of artificial errors. By comparing artificial data filtered by different levels of fluency, we find that artificial error sentences with low fluency can greatly facilitate error correction, while high fluency errors introduce more noise.
%R 10.18653/v1/W19-4408
%U https://aclanthology.org/W19-4408
%U https://doi.org/10.18653/v1/W19-4408
%P 87-91
Markdown (Informal)
[Artificial Error Generation with Fluency Filtering](https://aclanthology.org/W19-4408) (Qiu & Park, BEA 2019)
ACL
- Mengyang Qiu and Jungyeul Park. 2019. Artificial Error Generation with Fluency Filtering. In Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 87–91, Florence, Italy. Association for Computational Linguistics.