@inproceedings{kambhatla-etal-2022-cipherdaug,
title = "{C}ipher{DA}ug: Ciphertext based Data Augmentation for Neural Machine Translation",
author = "Kambhatla, Nishant and
Born, Logan and
Sarkar, Anoop",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.17",
doi = "10.18653/v1/2022.acl-long.17",
pages = "201--218",
abstract = "We propose a novel data-augmentation technique for neural machine translation based on ROT-$k$ ciphertexts. ROT-$k$ is a simple letter substitution cipher that replaces a letter in the plaintext with the $k$th letter after it in the alphabet. We first generate multiple ROT-$k$ ciphertexts using different values of $k$ for the plaintext which is the source side of the parallel data. We then leverage this enciphered training data along with the original parallel data via multi-source training to improve neural machine translation. Our method, CipherDAug, uses a co-regularization-inspired training procedure, requires no external data sources other than the original training data, and uses a standard Transformer to outperform strong data augmentation techniques on several datasets by a significant margin. This technique combines easily with existing approaches to data augmentation, and yields particularly strong results in low-resource settings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kambhatla-etal-2022-cipherdaug">
<titleInfo>
<title>CipherDAug: Ciphertext based Data Augmentation for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nishant</namePart>
<namePart type="family">Kambhatla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Logan</namePart>
<namePart type="family">Born</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Sarkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose a novel data-augmentation technique for neural machine translation based on ROT-k ciphertexts. ROT-k is a simple letter substitution cipher that replaces a letter in the plaintext with the kth letter after it in the alphabet. We first generate multiple ROT-k ciphertexts using different values of k for the plaintext which is the source side of the parallel data. We then leverage this enciphered training data along with the original parallel data via multi-source training to improve neural machine translation. Our method, CipherDAug, uses a co-regularization-inspired training procedure, requires no external data sources other than the original training data, and uses a standard Transformer to outperform strong data augmentation techniques on several datasets by a significant margin. This technique combines easily with existing approaches to data augmentation, and yields particularly strong results in low-resource settings.</abstract>
<identifier type="citekey">kambhatla-etal-2022-cipherdaug</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.17</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.17</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>201</start>
<end>218</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CipherDAug: Ciphertext based Data Augmentation for Neural Machine Translation
%A Kambhatla, Nishant
%A Born, Logan
%A Sarkar, Anoop
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F kambhatla-etal-2022-cipherdaug
%X We propose a novel data-augmentation technique for neural machine translation based on ROT-k ciphertexts. ROT-k is a simple letter substitution cipher that replaces a letter in the plaintext with the kth letter after it in the alphabet. We first generate multiple ROT-k ciphertexts using different values of k for the plaintext which is the source side of the parallel data. We then leverage this enciphered training data along with the original parallel data via multi-source training to improve neural machine translation. Our method, CipherDAug, uses a co-regularization-inspired training procedure, requires no external data sources other than the original training data, and uses a standard Transformer to outperform strong data augmentation techniques on several datasets by a significant margin. This technique combines easily with existing approaches to data augmentation, and yields particularly strong results in low-resource settings.
%R 10.18653/v1/2022.acl-long.17
%U https://aclanthology.org/2022.acl-long.17
%U https://doi.org/10.18653/v1/2022.acl-long.17
%P 201-218
Markdown (Informal)
[CipherDAug: Ciphertext based Data Augmentation for Neural Machine Translation](https://aclanthology.org/2022.acl-long.17) (Kambhatla et al., ACL 2022)
ACL