@inproceedings{burchell-birch-and-kenneth-heafield-2022-exploring,
title = "Exploring diversity in back translation for low-resource machine translation",
author = "Burchell, Laurie and
Birch, Alexandra and
Heafield, Kenneth",
editor = "Cherry, Colin and
Fan, Angela and
Foster, George and
Haffari, Gholamreza (Reza) and
Khadivi, Shahram and
Peng, Nanyun (Violet) and
Ren, Xiang and
Shareghi, Ehsan and
Swayamdipta, Swabha",
booktitle = "Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing",
month = jul,
year = "2022",
address = "Hybrid",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.deeplo-1.8",
doi = "10.18653/v1/2022.deeplo-1.8",
pages = "67--79",
abstract = "Back translation is one of the most widely used methods for improving the performance of neural machine translation systems. Recent research has sought to enhance the effectiveness of this method by increasing the {`}diversity{'} of the generated translations. We argue that the definitions and metrics used to quantify {`}diversity{'} in previous work have been insufficient. This work puts forward a more nuanced framework for understanding diversity in training data, splitting it into lexical diversity and syntactic diversity. We present novel metrics for measuring these different aspects of diversity and carry out empirical analysis into the effect of these types of diversity on final neural machine translation model performance for low-resource English↔Turkish and mid-resource English↔Icelandic. Our findings show that generating back translation using nucleus sampling results in higher final model performance, and that this method of generation has high levels of both lexical and syntactic diversity. We also find evidence that lexical diversity is more important than syntactic for back translation performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="burchell-birch-and-kenneth-heafield-2022-exploring">
<titleInfo>
<title>Exploring diversity in back translation for low-resource machine translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Laurie</namePart>
<namePart type="family">Burchell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Birch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenneth</namePart>
<namePart type="family">Heafield</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Colin</namePart>
<namePart type="family">Cherry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Foster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="given">(Reza)</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shahram</namePart>
<namePart type="family">Khadivi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanyun</namePart>
<namePart type="given">(Violet)</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Shareghi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hybrid</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Back translation is one of the most widely used methods for improving the performance of neural machine translation systems. Recent research has sought to enhance the effectiveness of this method by increasing the ‘diversity’ of the generated translations. We argue that the definitions and metrics used to quantify ‘diversity’ in previous work have been insufficient. This work puts forward a more nuanced framework for understanding diversity in training data, splitting it into lexical diversity and syntactic diversity. We present novel metrics for measuring these different aspects of diversity and carry out empirical analysis into the effect of these types of diversity on final neural machine translation model performance for low-resource English↔Turkish and mid-resource English↔Icelandic. Our findings show that generating back translation using nucleus sampling results in higher final model performance, and that this method of generation has high levels of both lexical and syntactic diversity. We also find evidence that lexical diversity is more important than syntactic for back translation performance.</abstract>
<identifier type="citekey">burchell-birch-and-kenneth-heafield-2022-exploring</identifier>
<identifier type="doi">10.18653/v1/2022.deeplo-1.8</identifier>
<location>
<url>https://aclanthology.org/2022.deeplo-1.8</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>67</start>
<end>79</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring diversity in back translation for low-resource machine translation
%A Burchell, Laurie
%A Birch, Alexandra
%A Heafield, Kenneth
%Y Cherry, Colin
%Y Fan, Angela
%Y Foster, George
%Y Haffari, Gholamreza (Reza)
%Y Khadivi, Shahram
%Y Peng, Nanyun (Violet)
%Y Ren, Xiang
%Y Shareghi, Ehsan
%Y Swayamdipta, Swabha
%S Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing
%D 2022
%8 July
%I Association for Computational Linguistics
%C Hybrid
%F burchell-birch-and-kenneth-heafield-2022-exploring
%X Back translation is one of the most widely used methods for improving the performance of neural machine translation systems. Recent research has sought to enhance the effectiveness of this method by increasing the ‘diversity’ of the generated translations. We argue that the definitions and metrics used to quantify ‘diversity’ in previous work have been insufficient. This work puts forward a more nuanced framework for understanding diversity in training data, splitting it into lexical diversity and syntactic diversity. We present novel metrics for measuring these different aspects of diversity and carry out empirical analysis into the effect of these types of diversity on final neural machine translation model performance for low-resource English↔Turkish and mid-resource English↔Icelandic. Our findings show that generating back translation using nucleus sampling results in higher final model performance, and that this method of generation has high levels of both lexical and syntactic diversity. We also find evidence that lexical diversity is more important than syntactic for back translation performance.
%R 10.18653/v1/2022.deeplo-1.8
%U https://aclanthology.org/2022.deeplo-1.8
%U https://doi.org/10.18653/v1/2022.deeplo-1.8
%P 67-79
Markdown (Informal)
[Exploring diversity in back translation for low-resource machine translation](https://aclanthology.org/2022.deeplo-1.8) (Burchell et al., DeepLo 2022)
ACL