@inproceedings{stahlberg-kumar-2021-synthetic,
title = "Synthetic Data Generation for Grammatical Error Correction with Tagged Corruption Models",
author = "Stahlberg, Felix and
Kumar, Shankar",
editor = "Burstein, Jill and
Horbach, Andrea and
Kochmar, Ekaterina and
Laarmann-Quante, Ronja and
Leacock, Claudia and
Madnani, Nitin and
Pil{\'a}n, Ildik{\'o} and
Yannakoudakis, Helen and
Zesch, Torsten",
booktitle = "Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.bea-1.4",
pages = "37--47",
abstract = "Synthetic data generation is widely known to boost the accuracy of neural grammatical error correction (GEC) systems, but existing methods often lack diversity or are too simplistic to generate the broad range of grammatical errors made by human writers. In this work, we use error type tags from automatic annotation tools such as ERRANT to guide synthetic data generation. We compare several models that can produce an ungrammatical sentence given a clean sentence and an error type tag. We use these models to build a new, large synthetic pre-training data set with error tag frequency distributions matching a given development set. Our synthetic data set yields large and consistent gains, improving the state-of-the-art on the BEA-19 and CoNLL-14 test sets. We also show that our approach is particularly effective in adapting a GEC system, trained on mixed native and non-native English, to a native English test set, even surpassing real training data consisting of high-quality sentence pairs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stahlberg-kumar-2021-synthetic">
<titleInfo>
<title>Synthetic Data Generation for Grammatical Error Correction with Tagged Corruption Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Stahlberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shankar</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</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">Ronja</namePart>
<namePart type="family">Laarmann-Quante</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">Helen</namePart>
<namePart type="family">Yannakoudakis</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">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Synthetic data generation is widely known to boost the accuracy of neural grammatical error correction (GEC) systems, but existing methods often lack diversity or are too simplistic to generate the broad range of grammatical errors made by human writers. In this work, we use error type tags from automatic annotation tools such as ERRANT to guide synthetic data generation. We compare several models that can produce an ungrammatical sentence given a clean sentence and an error type tag. We use these models to build a new, large synthetic pre-training data set with error tag frequency distributions matching a given development set. Our synthetic data set yields large and consistent gains, improving the state-of-the-art on the BEA-19 and CoNLL-14 test sets. We also show that our approach is particularly effective in adapting a GEC system, trained on mixed native and non-native English, to a native English test set, even surpassing real training data consisting of high-quality sentence pairs.</abstract>
<identifier type="citekey">stahlberg-kumar-2021-synthetic</identifier>
<location>
<url>https://aclanthology.org/2021.bea-1.4</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>37</start>
<end>47</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Synthetic Data Generation for Grammatical Error Correction with Tagged Corruption Models
%A Stahlberg, Felix
%A Kumar, Shankar
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Kochmar, Ekaterina
%Y Laarmann-Quante, Ronja
%Y Leacock, Claudia
%Y Madnani, Nitin
%Y Pilán, Ildikó
%Y Yannakoudakis, Helen
%Y Zesch, Torsten
%S Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F stahlberg-kumar-2021-synthetic
%X Synthetic data generation is widely known to boost the accuracy of neural grammatical error correction (GEC) systems, but existing methods often lack diversity or are too simplistic to generate the broad range of grammatical errors made by human writers. In this work, we use error type tags from automatic annotation tools such as ERRANT to guide synthetic data generation. We compare several models that can produce an ungrammatical sentence given a clean sentence and an error type tag. We use these models to build a new, large synthetic pre-training data set with error tag frequency distributions matching a given development set. Our synthetic data set yields large and consistent gains, improving the state-of-the-art on the BEA-19 and CoNLL-14 test sets. We also show that our approach is particularly effective in adapting a GEC system, trained on mixed native and non-native English, to a native English test set, even surpassing real training data consisting of high-quality sentence pairs.
%U https://aclanthology.org/2021.bea-1.4
%P 37-47
Markdown (Informal)
[Synthetic Data Generation for Grammatical Error Correction with Tagged Corruption Models](https://aclanthology.org/2021.bea-1.4) (Stahlberg & Kumar, BEA 2021)
ACL