@inproceedings{rama-vanmassenhove-2021-comparison,
title = "A Comparison of Different {NMT} Approaches to Low-Resource {D}utch-{A}lbanian Machine Translation",
author = "Rama, Arbnor and
Vanmassenhove, Eva",
editor = "Ortega, John and
Ojha, Atul Kr. and
Kann, Katharina and
Liu, Chao-Hong",
booktitle = "Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021)",
month = aug,
year = "2021",
address = "Virtual",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2021.mtsummit-loresmt.7",
pages = "68--77",
abstract = "Low-resource languages can be understood as languages that are more scarce, less studied, less privileged, less commonly taught and for which there are less resources available (Singh, 2008; Cieri et al., 2016; Magueresse et al., 2020). Natural Language Processing (NLP) research and technology mainly focuses on those languages for which there are large data sets available. To illustrate differences in data availability: there are 6 million Wikipedia articles available for English, 2 million for Dutch, and merely 82 thousand for Albanian. The scarce data issue becomes increasingly apparent when large parallel data sets are required for applications such as Neural Machine Translation (NMT). In this work, we investigate to what extent translation between Albanian (SQ) and Dutch (NL) is possible comparing a one-to-one (SQ↔AL) model, a low-resource pivot-based approach (English (EN) as pivot) and a zero-shot translation (ZST) (Johnson et al., 2016; Mattoni et al., 2017) system. From our experiments, it results that the EN-pivot-model outperforms both the direct one-to-one and the ZST model. Since often, small amounts of parallel data are available for low-resource languages or settings, experiments were conducted using small sets of parallel NL↔SQ data. The ZST appeared to be the worst performing models. Even when the available parallel data (NL↔SQ) was added, i.e. in a few-shot setting (FST), it remained the worst performing system according to the automatic (BLEU and TER) and human evaluation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rama-vanmassenhove-2021-comparison">
<titleInfo>
<title>A Comparison of Different NMT Approaches to Low-Resource Dutch-Albanian Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arbnor</namePart>
<namePart type="family">Rama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Vanmassenhove</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Ortega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">Kann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-Hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">Virtual</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Low-resource languages can be understood as languages that are more scarce, less studied, less privileged, less commonly taught and for which there are less resources available (Singh, 2008; Cieri et al., 2016; Magueresse et al., 2020). Natural Language Processing (NLP) research and technology mainly focuses on those languages for which there are large data sets available. To illustrate differences in data availability: there are 6 million Wikipedia articles available for English, 2 million for Dutch, and merely 82 thousand for Albanian. The scarce data issue becomes increasingly apparent when large parallel data sets are required for applications such as Neural Machine Translation (NMT). In this work, we investigate to what extent translation between Albanian (SQ) and Dutch (NL) is possible comparing a one-to-one (SQ↔AL) model, a low-resource pivot-based approach (English (EN) as pivot) and a zero-shot translation (ZST) (Johnson et al., 2016; Mattoni et al., 2017) system. From our experiments, it results that the EN-pivot-model outperforms both the direct one-to-one and the ZST model. Since often, small amounts of parallel data are available for low-resource languages or settings, experiments were conducted using small sets of parallel NL↔SQ data. The ZST appeared to be the worst performing models. Even when the available parallel data (NL↔SQ) was added, i.e. in a few-shot setting (FST), it remained the worst performing system according to the automatic (BLEU and TER) and human evaluation.</abstract>
<identifier type="citekey">rama-vanmassenhove-2021-comparison</identifier>
<location>
<url>https://aclanthology.org/2021.mtsummit-loresmt.7</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>68</start>
<end>77</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Comparison of Different NMT Approaches to Low-Resource Dutch-Albanian Machine Translation
%A Rama, Arbnor
%A Vanmassenhove, Eva
%Y Ortega, John
%Y Ojha, Atul Kr.
%Y Kann, Katharina
%Y Liu, Chao-Hong
%S Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021)
%D 2021
%8 August
%I Association for Machine Translation in the Americas
%C Virtual
%F rama-vanmassenhove-2021-comparison
%X Low-resource languages can be understood as languages that are more scarce, less studied, less privileged, less commonly taught and for which there are less resources available (Singh, 2008; Cieri et al., 2016; Magueresse et al., 2020). Natural Language Processing (NLP) research and technology mainly focuses on those languages for which there are large data sets available. To illustrate differences in data availability: there are 6 million Wikipedia articles available for English, 2 million for Dutch, and merely 82 thousand for Albanian. The scarce data issue becomes increasingly apparent when large parallel data sets are required for applications such as Neural Machine Translation (NMT). In this work, we investigate to what extent translation between Albanian (SQ) and Dutch (NL) is possible comparing a one-to-one (SQ↔AL) model, a low-resource pivot-based approach (English (EN) as pivot) and a zero-shot translation (ZST) (Johnson et al., 2016; Mattoni et al., 2017) system. From our experiments, it results that the EN-pivot-model outperforms both the direct one-to-one and the ZST model. Since often, small amounts of parallel data are available for low-resource languages or settings, experiments were conducted using small sets of parallel NL↔SQ data. The ZST appeared to be the worst performing models. Even when the available parallel data (NL↔SQ) was added, i.e. in a few-shot setting (FST), it remained the worst performing system according to the automatic (BLEU and TER) and human evaluation.
%U https://aclanthology.org/2021.mtsummit-loresmt.7
%P 68-77
Markdown (Informal)
[A Comparison of Different NMT Approaches to Low-Resource Dutch-Albanian Machine Translation](https://aclanthology.org/2021.mtsummit-loresmt.7) (Rama & Vanmassenhove, LoResMT 2021)
ACL