@inproceedings{xing-etal-2022-taking,
title = "Taking Actions Separately: A Bidirectionally-Adaptive Transfer Learning Method for Low-Resource Neural Machine Translation",
author = "Xing, Xiaolin and
Hong, Yu and
Xu, Minhan and
Yao, Jianmin and
Zhou, Guodong",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.395",
pages = "4481--4491",
abstract = "Training Neural Machine Translation (NMT) models suffers from sparse parallel data, in the infrequent translation scenarios towards low-resource source languages. The existing solutions primarily concentrate on the utilization of Parent-Child (PC) transfer learning. It transfers well-trained NMT models on high-resource languages (namely Parent NMT) to low-resource languages, so as to produce Child NMT models by fine-tuning. It has been carefully demonstrated that a variety of PC variants yield significant improvements for low-resource NMT. In this paper, we intend to enhance PC-based NMT by a bidirectionally-adaptive learning strategy. Specifically, we divide inner constituents (6 transformers) of Parent encoder into two {``}teams{''}, i.e., T1 and T2. During representation learning, T1 learns to encode low-resource languages conditioned on bilingual shareable latent space. Generative adversarial network and masked language modeling are used for space-shareable encoding. On the other hand, T2 is straightforwardly transferred to low-resource languages, and fine-tuned together with T1 for low-resource translation. Briefly, T1 and T2 take actions separately for different goals. The former aims to adapt to characteristics of low-resource languages during encoding, while the latter adapts to translation experiences learned from high-resource languages. We experiment on benchmark corpora SETIMES, conducting low-resource NMT for Albanian (Sq), Macedonian (Mk), Croatian (Hr) and Romanian (Ro). Experimental results show that our method yields substantial improvements, which allows the NMT performance to reach BLEU4-scores of 62.24{\%}, 56.93{\%}, 50.53{\%} and 54.65{\%} for Sq, Mk, Hr and Ro, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xing-etal-2022-taking">
<titleInfo>
<title>Taking Actions Separately: A Bidirectionally-Adaptive Transfer Learning Method for Low-Resource Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaolin</namePart>
<namePart type="family">Xing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minhan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianmin</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guodong</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Training Neural Machine Translation (NMT) models suffers from sparse parallel data, in the infrequent translation scenarios towards low-resource source languages. The existing solutions primarily concentrate on the utilization of Parent-Child (PC) transfer learning. It transfers well-trained NMT models on high-resource languages (namely Parent NMT) to low-resource languages, so as to produce Child NMT models by fine-tuning. It has been carefully demonstrated that a variety of PC variants yield significant improvements for low-resource NMT. In this paper, we intend to enhance PC-based NMT by a bidirectionally-adaptive learning strategy. Specifically, we divide inner constituents (6 transformers) of Parent encoder into two “teams”, i.e., T1 and T2. During representation learning, T1 learns to encode low-resource languages conditioned on bilingual shareable latent space. Generative adversarial network and masked language modeling are used for space-shareable encoding. On the other hand, T2 is straightforwardly transferred to low-resource languages, and fine-tuned together with T1 for low-resource translation. Briefly, T1 and T2 take actions separately for different goals. The former aims to adapt to characteristics of low-resource languages during encoding, while the latter adapts to translation experiences learned from high-resource languages. We experiment on benchmark corpora SETIMES, conducting low-resource NMT for Albanian (Sq), Macedonian (Mk), Croatian (Hr) and Romanian (Ro). Experimental results show that our method yields substantial improvements, which allows the NMT performance to reach BLEU4-scores of 62.24%, 56.93%, 50.53% and 54.65% for Sq, Mk, Hr and Ro, respectively.</abstract>
<identifier type="citekey">xing-etal-2022-taking</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.395</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>4481</start>
<end>4491</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Taking Actions Separately: A Bidirectionally-Adaptive Transfer Learning Method for Low-Resource Neural Machine Translation
%A Xing, Xiaolin
%A Hong, Yu
%A Xu, Minhan
%A Yao, Jianmin
%A Zhou, Guodong
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F xing-etal-2022-taking
%X Training Neural Machine Translation (NMT) models suffers from sparse parallel data, in the infrequent translation scenarios towards low-resource source languages. The existing solutions primarily concentrate on the utilization of Parent-Child (PC) transfer learning. It transfers well-trained NMT models on high-resource languages (namely Parent NMT) to low-resource languages, so as to produce Child NMT models by fine-tuning. It has been carefully demonstrated that a variety of PC variants yield significant improvements for low-resource NMT. In this paper, we intend to enhance PC-based NMT by a bidirectionally-adaptive learning strategy. Specifically, we divide inner constituents (6 transformers) of Parent encoder into two “teams”, i.e., T1 and T2. During representation learning, T1 learns to encode low-resource languages conditioned on bilingual shareable latent space. Generative adversarial network and masked language modeling are used for space-shareable encoding. On the other hand, T2 is straightforwardly transferred to low-resource languages, and fine-tuned together with T1 for low-resource translation. Briefly, T1 and T2 take actions separately for different goals. The former aims to adapt to characteristics of low-resource languages during encoding, while the latter adapts to translation experiences learned from high-resource languages. We experiment on benchmark corpora SETIMES, conducting low-resource NMT for Albanian (Sq), Macedonian (Mk), Croatian (Hr) and Romanian (Ro). Experimental results show that our method yields substantial improvements, which allows the NMT performance to reach BLEU4-scores of 62.24%, 56.93%, 50.53% and 54.65% for Sq, Mk, Hr and Ro, respectively.
%U https://aclanthology.org/2022.coling-1.395
%P 4481-4491
Markdown (Informal)
[Taking Actions Separately: A Bidirectionally-Adaptive Transfer Learning Method for Low-Resource Neural Machine Translation](https://aclanthology.org/2022.coling-1.395) (Xing et al., COLING 2022)
ACL