@inproceedings{kasewa-etal-2018-wronging,
title = "Wronging a Right: Generating Better Errors to Improve Grammatical Error Detection",
author = "Kasewa, Sudhanshu and
Stenetorp, Pontus and
Riedel, Sebastian",
editor = "Riloff, Ellen and
Chiang, David and
Hockenmaier, Julia and
Tsujii, Jun{'}ichi",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1541",
doi = "10.18653/v1/D18-1541",
pages = "4977--4983",
abstract = "Grammatical error correction, like other machine learning tasks, greatly benefits from large quantities of high quality training data, which is typically expensive to produce. While writing a program to automatically generate realistic grammatical errors would be difficult, one could learn the distribution of naturally-occurring errors and attempt to introduce them into other datasets. Initial work on inducing errors in this way using statistical machine translation has shown promise; we investigate cheaply constructing synthetic samples, given a small corpus of human-annotated data, using an off-the-rack attentive sequence-to-sequence model and a straight-forward post-processing procedure. Our approach yields error-filled artificial data that helps a vanilla bi-directional LSTM to outperform the previous state of the art at grammatical error detection, and a previously introduced model to gain further improvements of over 5{\%} F0.5 score. When attempting to determine if a given sentence is synthetic, a human annotator at best achieves 39.39 F1 score, indicating that our model generates mostly human-like instances.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kasewa-etal-2018-wronging">
<titleInfo>
<title>Wronging a Right: Generating Better Errors to Improve Grammatical Error Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sudhanshu</namePart>
<namePart type="family">Kasewa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pontus</namePart>
<namePart type="family">Stenetorp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Riedel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Riloff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Hockenmaier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun’ichi</namePart>
<namePart type="family">Tsujii</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>Grammatical error correction, like other machine learning tasks, greatly benefits from large quantities of high quality training data, which is typically expensive to produce. While writing a program to automatically generate realistic grammatical errors would be difficult, one could learn the distribution of naturally-occurring errors and attempt to introduce them into other datasets. Initial work on inducing errors in this way using statistical machine translation has shown promise; we investigate cheaply constructing synthetic samples, given a small corpus of human-annotated data, using an off-the-rack attentive sequence-to-sequence model and a straight-forward post-processing procedure. Our approach yields error-filled artificial data that helps a vanilla bi-directional LSTM to outperform the previous state of the art at grammatical error detection, and a previously introduced model to gain further improvements of over 5% F0.5 score. When attempting to determine if a given sentence is synthetic, a human annotator at best achieves 39.39 F1 score, indicating that our model generates mostly human-like instances.</abstract>
<identifier type="citekey">kasewa-etal-2018-wronging</identifier>
<identifier type="doi">10.18653/v1/D18-1541</identifier>
<location>
<url>https://aclanthology.org/D18-1541</url>
</location>
<part>
<date>2018-oct-nov</date>
<extent unit="page">
<start>4977</start>
<end>4983</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Wronging a Right: Generating Better Errors to Improve Grammatical Error Detection
%A Kasewa, Sudhanshu
%A Stenetorp, Pontus
%A Riedel, Sebastian
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F kasewa-etal-2018-wronging
%X Grammatical error correction, like other machine learning tasks, greatly benefits from large quantities of high quality training data, which is typically expensive to produce. While writing a program to automatically generate realistic grammatical errors would be difficult, one could learn the distribution of naturally-occurring errors and attempt to introduce them into other datasets. Initial work on inducing errors in this way using statistical machine translation has shown promise; we investigate cheaply constructing synthetic samples, given a small corpus of human-annotated data, using an off-the-rack attentive sequence-to-sequence model and a straight-forward post-processing procedure. Our approach yields error-filled artificial data that helps a vanilla bi-directional LSTM to outperform the previous state of the art at grammatical error detection, and a previously introduced model to gain further improvements of over 5% F0.5 score. When attempting to determine if a given sentence is synthetic, a human annotator at best achieves 39.39 F1 score, indicating that our model generates mostly human-like instances.
%R 10.18653/v1/D18-1541
%U https://aclanthology.org/D18-1541
%U https://doi.org/10.18653/v1/D18-1541
%P 4977-4983
Markdown (Informal)
[Wronging a Right: Generating Better Errors to Improve Grammatical Error Detection](https://aclanthology.org/D18-1541) (Kasewa et al., EMNLP 2018)
ACL