@inproceedings{pang-etal-2024-monmt-modularly,
title = "{M}o{NMT}: Modularly Leveraging Monolingual and Bilingual Knowledge for Neural Machine Translation",
author = "Pang, Jianhui and
Yang, Baosong and
Wong, Derek F. and
Liu, Dayiheng and
Wei, Xiangpeng and
Xie, Jun and
Chao, Lidia S.",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1010",
pages = "11560--11573",
abstract = "The effective use of monolingual and bilingual knowledge represents a critical challenge within the neural machine translation (NMT) community. In this paper, we propose a modular strategy that facilitates the cooperation of these two types of knowledge in translation tasks, while avoiding the issue of catastrophic forgetting and exhibiting superior model generalization and robustness. Our model is comprised of three functionally independent modules: an encoding module, a decoding module, and a transferring module. The former two acquire large-scale monolingual knowledge via self-supervised learning, while the latter is trained on parallel data and responsible for transferring latent features between the encoding and decoding modules. Extensive experiments in multi-domain translation tasks indicate our model yields remarkable performance, with up to 7 BLEU improvements in out-of-domain tests over the conventional pretrain-and-finetune approach. Our codes are available at https://github.com/NLP2CT/MoNMT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pang-etal-2024-monmt-modularly">
<titleInfo>
<title>MoNMT: Modularly Leveraging Monolingual and Bilingual Knowledge for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jianhui</namePart>
<namePart type="family">Pang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baosong</namePart>
<namePart type="family">Yang</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">Dayiheng</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangpeng</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Xie</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>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</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>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The effective use of monolingual and bilingual knowledge represents a critical challenge within the neural machine translation (NMT) community. In this paper, we propose a modular strategy that facilitates the cooperation of these two types of knowledge in translation tasks, while avoiding the issue of catastrophic forgetting and exhibiting superior model generalization and robustness. Our model is comprised of three functionally independent modules: an encoding module, a decoding module, and a transferring module. The former two acquire large-scale monolingual knowledge via self-supervised learning, while the latter is trained on parallel data and responsible for transferring latent features between the encoding and decoding modules. Extensive experiments in multi-domain translation tasks indicate our model yields remarkable performance, with up to 7 BLEU improvements in out-of-domain tests over the conventional pretrain-and-finetune approach. Our codes are available at https://github.com/NLP2CT/MoNMT.</abstract>
<identifier type="citekey">pang-etal-2024-monmt-modularly</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1010</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>11560</start>
<end>11573</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MoNMT: Modularly Leveraging Monolingual and Bilingual Knowledge for Neural Machine Translation
%A Pang, Jianhui
%A Yang, Baosong
%A Wong, Derek F.
%A Liu, Dayiheng
%A Wei, Xiangpeng
%A Xie, Jun
%A Chao, Lidia S.
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F pang-etal-2024-monmt-modularly
%X The effective use of monolingual and bilingual knowledge represents a critical challenge within the neural machine translation (NMT) community. In this paper, we propose a modular strategy that facilitates the cooperation of these two types of knowledge in translation tasks, while avoiding the issue of catastrophic forgetting and exhibiting superior model generalization and robustness. Our model is comprised of three functionally independent modules: an encoding module, a decoding module, and a transferring module. The former two acquire large-scale monolingual knowledge via self-supervised learning, while the latter is trained on parallel data and responsible for transferring latent features between the encoding and decoding modules. Extensive experiments in multi-domain translation tasks indicate our model yields remarkable performance, with up to 7 BLEU improvements in out-of-domain tests over the conventional pretrain-and-finetune approach. Our codes are available at https://github.com/NLP2CT/MoNMT.
%U https://aclanthology.org/2024.lrec-main.1010
%P 11560-11573
Markdown (Informal)
[MoNMT: Modularly Leveraging Monolingual and Bilingual Knowledge for Neural Machine Translation](https://aclanthology.org/2024.lrec-main.1010) (Pang et al., LREC-COLING 2024)
ACL
- Jianhui Pang, Baosong Yang, Derek F. Wong, Dayiheng Liu, Xiangpeng Wei, Jun Xie, and Lidia S. Chao. 2024. MoNMT: Modularly Leveraging Monolingual and Bilingual Knowledge for Neural Machine Translation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 11560–11573, Torino, Italia. ELRA and ICCL.