@inproceedings{li-etal-2022-consisttl,
title = "{C}onsist{TL}: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translation",
author = "Li, Zhaocong and
Liu, Xuebo and
Wong, Derek F. and
Chao, Lidia S. and
Zhang, Min",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.574",
doi = "10.18653/v1/2022.emnlp-main.574",
pages = "8383--8394",
abstract = "Transfer learning is a simple and powerful method that can be used to boost model performance of low-resource neural machine translation (NMT). Existing transfer learning methods for NMT are static, which simply transfer knowledge from a parent model to a child model once via parameter initialization. In this paper, we propose a novel transfer learning method for NMT, namely ConsistTL, which can continuously transfer knowledge from the parent model during the training of the child model. Specifically, for each training instance of the child model, ConsistTL constructs the semantically-equivalent instance for the parent model and encourages prediction consistency between the parent and child for this instance, which is equivalent to the child model learning each instance under the guidance of the parent model. Experimental results on five low-resource NMT tasks demonstrate that ConsistTL results in significant improvements over strong transfer learning baselines, with a gain up to 1.7 BLEU over the existing back-translation model on the widely-used WMT17 Turkish-English benchmark. Further analysis reveals that ConsistTL can improve the inference calibration of the child model. Code and scripts are freely available at \url{https://github.com/NLP2CT/ConsistTL}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2022-consisttl">
<titleInfo>
<title>ConsistTL: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhaocong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuebo</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lidia</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Chao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Transfer learning is a simple and powerful method that can be used to boost model performance of low-resource neural machine translation (NMT). Existing transfer learning methods for NMT are static, which simply transfer knowledge from a parent model to a child model once via parameter initialization. In this paper, we propose a novel transfer learning method for NMT, namely ConsistTL, which can continuously transfer knowledge from the parent model during the training of the child model. Specifically, for each training instance of the child model, ConsistTL constructs the semantically-equivalent instance for the parent model and encourages prediction consistency between the parent and child for this instance, which is equivalent to the child model learning each instance under the guidance of the parent model. Experimental results on five low-resource NMT tasks demonstrate that ConsistTL results in significant improvements over strong transfer learning baselines, with a gain up to 1.7 BLEU over the existing back-translation model on the widely-used WMT17 Turkish-English benchmark. Further analysis reveals that ConsistTL can improve the inference calibration of the child model. Code and scripts are freely available at https://github.com/NLP2CT/ConsistTL.</abstract>
<identifier type="citekey">li-etal-2022-consisttl</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.574</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.574</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>8383</start>
<end>8394</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ConsistTL: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translation
%A Li, Zhaocong
%A Liu, Xuebo
%A Wong, Derek F.
%A Chao, Lidia S.
%A Zhang, Min
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F li-etal-2022-consisttl
%X Transfer learning is a simple and powerful method that can be used to boost model performance of low-resource neural machine translation (NMT). Existing transfer learning methods for NMT are static, which simply transfer knowledge from a parent model to a child model once via parameter initialization. In this paper, we propose a novel transfer learning method for NMT, namely ConsistTL, which can continuously transfer knowledge from the parent model during the training of the child model. Specifically, for each training instance of the child model, ConsistTL constructs the semantically-equivalent instance for the parent model and encourages prediction consistency between the parent and child for this instance, which is equivalent to the child model learning each instance under the guidance of the parent model. Experimental results on five low-resource NMT tasks demonstrate that ConsistTL results in significant improvements over strong transfer learning baselines, with a gain up to 1.7 BLEU over the existing back-translation model on the widely-used WMT17 Turkish-English benchmark. Further analysis reveals that ConsistTL can improve the inference calibration of the child model. Code and scripts are freely available at https://github.com/NLP2CT/ConsistTL.
%R 10.18653/v1/2022.emnlp-main.574
%U https://aclanthology.org/2022.emnlp-main.574
%U https://doi.org/10.18653/v1/2022.emnlp-main.574
%P 8383-8394
Markdown (Informal)
[ConsistTL: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translation](https://aclanthology.org/2022.emnlp-main.574) (Li et al., EMNLP 2022)
ACL