@inproceedings{zomer-frankenberg-garcia-2021-beyond-grammatical,
title = "Beyond Grammatical Error Correction: Improving {L}1-influenced research writing in {E}nglish using pre-trained encoder-decoder models",
author = "Zomer, Gustavo and
Frankenberg-Garcia, Ana",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.216",
doi = "10.18653/v1/2021.findings-emnlp.216",
pages = "2534--2540",
abstract = "In this paper, we present a new method for training a writing improvement model adapted to the writer{'}s first language (L1) that goes beyond grammatical error correction (GEC). Without using annotated training data, we rely solely on pre-trained language models fine-tuned with parallel corpora of reference translation aligned with machine translation. We evaluate our model with corpora of academic papers written in English by L1 Portuguese and L1 Spanish scholars and a reference corpus of expert academic English. We show that our model is able to address specific L1-influenced writing and more complex linguistic phenomena than existing methods, outperforming what a state-of-the-art GEC system can achieve in this regard. Our code and data are open to other researchers.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zomer-frankenberg-garcia-2021-beyond-grammatical">
<titleInfo>
<title>Beyond Grammatical Error Correction: Improving L1-influenced research writing in English using pre-trained encoder-decoder models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gustavo</namePart>
<namePart type="family">Zomer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="family">Frankenberg-Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present a new method for training a writing improvement model adapted to the writer’s first language (L1) that goes beyond grammatical error correction (GEC). Without using annotated training data, we rely solely on pre-trained language models fine-tuned with parallel corpora of reference translation aligned with machine translation. We evaluate our model with corpora of academic papers written in English by L1 Portuguese and L1 Spanish scholars and a reference corpus of expert academic English. We show that our model is able to address specific L1-influenced writing and more complex linguistic phenomena than existing methods, outperforming what a state-of-the-art GEC system can achieve in this regard. Our code and data are open to other researchers.</abstract>
<identifier type="citekey">zomer-frankenberg-garcia-2021-beyond-grammatical</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.216</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.216</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>2534</start>
<end>2540</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Grammatical Error Correction: Improving L1-influenced research writing in English using pre-trained encoder-decoder models
%A Zomer, Gustavo
%A Frankenberg-Garcia, Ana
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F zomer-frankenberg-garcia-2021-beyond-grammatical
%X In this paper, we present a new method for training a writing improvement model adapted to the writer’s first language (L1) that goes beyond grammatical error correction (GEC). Without using annotated training data, we rely solely on pre-trained language models fine-tuned with parallel corpora of reference translation aligned with machine translation. We evaluate our model with corpora of academic papers written in English by L1 Portuguese and L1 Spanish scholars and a reference corpus of expert academic English. We show that our model is able to address specific L1-influenced writing and more complex linguistic phenomena than existing methods, outperforming what a state-of-the-art GEC system can achieve in this regard. Our code and data are open to other researchers.
%R 10.18653/v1/2021.findings-emnlp.216
%U https://aclanthology.org/2021.findings-emnlp.216
%U https://doi.org/10.18653/v1/2021.findings-emnlp.216
%P 2534-2540
Markdown (Informal)
[Beyond Grammatical Error Correction: Improving L1-influenced research writing in English using pre-trained encoder-decoder models](https://aclanthology.org/2021.findings-emnlp.216) (Zomer & Frankenberg-Garcia, Findings 2021)
ACL