@inproceedings{chakrabarty-etal-2020-improving,
title = "Improving Low-Resource {NMT} through Relevance Based Linguistic Features Incorporation",
author = "Chakrabarty, Abhisek and
Dabre, Raj and
Ding, Chenchen and
Utiyama, Masao and
Sumita, Eiichiro",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.376",
doi = "10.18653/v1/2020.coling-main.376",
pages = "4263--4274",
abstract = "In this study, linguistic knowledge at different levels are incorporated into the neural machine translation (NMT) framework to improve translation quality for language pairs with extremely limited data. Integrating manually designed or automatically extracted features into the NMT framework is known to be beneficial. However, this study emphasizes that the relevance of the features is crucial to the performance. Specifically, we propose two methods, 1) self relevance and 2) word-based relevance, to improve the representation of features for NMT. Experiments are conducted on translation tasks from English to eight Asian languages, with no more than twenty thousand sentences for training. The proposed methods improve translation quality for all tasks by up to 3.09 BLEU points. Discussions with visualization provide the explainability of the proposed methods where we show that the relevance methods provide weights to features thereby enhancing their impact on low-resource machine translation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chakrabarty-etal-2020-improving">
<titleInfo>
<title>Improving Low-Resource NMT through Relevance Based Linguistic Features Incorporation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abhisek</namePart>
<namePart type="family">Chakrabarty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="family">Dabre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenchen</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eiichiro</namePart>
<namePart type="family">Sumita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this study, linguistic knowledge at different levels are incorporated into the neural machine translation (NMT) framework to improve translation quality for language pairs with extremely limited data. Integrating manually designed or automatically extracted features into the NMT framework is known to be beneficial. However, this study emphasizes that the relevance of the features is crucial to the performance. Specifically, we propose two methods, 1) self relevance and 2) word-based relevance, to improve the representation of features for NMT. Experiments are conducted on translation tasks from English to eight Asian languages, with no more than twenty thousand sentences for training. The proposed methods improve translation quality for all tasks by up to 3.09 BLEU points. Discussions with visualization provide the explainability of the proposed methods where we show that the relevance methods provide weights to features thereby enhancing their impact on low-resource machine translation.</abstract>
<identifier type="citekey">chakrabarty-etal-2020-improving</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.376</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.376</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>4263</start>
<end>4274</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Low-Resource NMT through Relevance Based Linguistic Features Incorporation
%A Chakrabarty, Abhisek
%A Dabre, Raj
%A Ding, Chenchen
%A Utiyama, Masao
%A Sumita, Eiichiro
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F chakrabarty-etal-2020-improving
%X In this study, linguistic knowledge at different levels are incorporated into the neural machine translation (NMT) framework to improve translation quality for language pairs with extremely limited data. Integrating manually designed or automatically extracted features into the NMT framework is known to be beneficial. However, this study emphasizes that the relevance of the features is crucial to the performance. Specifically, we propose two methods, 1) self relevance and 2) word-based relevance, to improve the representation of features for NMT. Experiments are conducted on translation tasks from English to eight Asian languages, with no more than twenty thousand sentences for training. The proposed methods improve translation quality for all tasks by up to 3.09 BLEU points. Discussions with visualization provide the explainability of the proposed methods where we show that the relevance methods provide weights to features thereby enhancing their impact on low-resource machine translation.
%R 10.18653/v1/2020.coling-main.376
%U https://aclanthology.org/2020.coling-main.376
%U https://doi.org/10.18653/v1/2020.coling-main.376
%P 4263-4274
Markdown (Informal)
[Improving Low-Resource NMT through Relevance Based Linguistic Features Incorporation](https://aclanthology.org/2020.coling-main.376) (Chakrabarty et al., COLING 2020)
ACL