@inproceedings{signoroni-rychly-2023-evaluating,
title = "Evaluating Sentence Alignment Methods in a Low-Resource Setting: An {E}nglish-{Y}or{\`u}{B}{\'a} Study Case",
author = "Signoroni, Edoardo and
Rychl{\'y}, Pavel",
editor = "Ojha, Atul Kr. and
Liu, Chao-hong and
Vylomova, Ekaterina and
Pirinen, Flammie and
Abbott, Jade and
Washington, Jonathan and
Oco, Nathaniel and
Malykh, Valentin and
Logacheva, Varvara and
Zhao, Xiaobing",
booktitle = "Proceedings of the Sixth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2023)",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.loresmt-1.10",
doi = "10.18653/v1/2023.loresmt-1.10",
pages = "123--129",
abstract = "Parallel corpora are still crucial to train effective Machine Translation systems. This is even more true for low-resource language pairs, for which Neural Machine Translation has been shown to be less robust to domain mismatch and noise. Due to time and resource constraints, parallel corpora are mostly created with sentence alignment methods which automatically infer alignments. Recent work focused on state-of-the-art pre-trained sentence embeddings-based methods which are available only for a tiny fraction of the world{'}s languages. In this paper, we evaluate the performance of four widely used algorithms on the low-resource English-Yor{\`u}b{\'a} language pair against a multidomain benchmark parallel corpus on two experiments involving 1-to-1 alignments with and without reordering. We find that, at least for this language pair, earlier and simpler methods are more suited to the task, all the while not requiring additional data or resources. We also report that the methods we evaluated perform differently across distinct domains, thus indicating that some approach may be better for a specific domain or textual structure.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="signoroni-rychly-2023-evaluating">
<titleInfo>
<title>Evaluating Sentence Alignment Methods in a Low-Resource Setting: An English-YorùBá Study Case</title>
</titleInfo>
<name type="personal">
<namePart type="given">Edoardo</namePart>
<namePart type="family">Signoroni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Rychlý</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2023)</title>
</titleInfo>
<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">Chao-hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flammie</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jade</namePart>
<namePart type="family">Abbott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Washington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Oco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Malykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varvara</namePart>
<namePart type="family">Logacheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobing</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Parallel corpora are still crucial to train effective Machine Translation systems. This is even more true for low-resource language pairs, for which Neural Machine Translation has been shown to be less robust to domain mismatch and noise. Due to time and resource constraints, parallel corpora are mostly created with sentence alignment methods which automatically infer alignments. Recent work focused on state-of-the-art pre-trained sentence embeddings-based methods which are available only for a tiny fraction of the world’s languages. In this paper, we evaluate the performance of four widely used algorithms on the low-resource English-Yorùbá language pair against a multidomain benchmark parallel corpus on two experiments involving 1-to-1 alignments with and without reordering. We find that, at least for this language pair, earlier and simpler methods are more suited to the task, all the while not requiring additional data or resources. We also report that the methods we evaluated perform differently across distinct domains, thus indicating that some approach may be better for a specific domain or textual structure.</abstract>
<identifier type="citekey">signoroni-rychly-2023-evaluating</identifier>
<identifier type="doi">10.18653/v1/2023.loresmt-1.10</identifier>
<location>
<url>https://aclanthology.org/2023.loresmt-1.10</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>123</start>
<end>129</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Sentence Alignment Methods in a Low-Resource Setting: An English-YorùBá Study Case
%A Signoroni, Edoardo
%A Rychlý, Pavel
%Y Ojha, Atul Kr.
%Y Liu, Chao-hong
%Y Vylomova, Ekaterina
%Y Pirinen, Flammie
%Y Abbott, Jade
%Y Washington, Jonathan
%Y Oco, Nathaniel
%Y Malykh, Valentin
%Y Logacheva, Varvara
%Y Zhao, Xiaobing
%S Proceedings of the Sixth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2023)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F signoroni-rychly-2023-evaluating
%X Parallel corpora are still crucial to train effective Machine Translation systems. This is even more true for low-resource language pairs, for which Neural Machine Translation has been shown to be less robust to domain mismatch and noise. Due to time and resource constraints, parallel corpora are mostly created with sentence alignment methods which automatically infer alignments. Recent work focused on state-of-the-art pre-trained sentence embeddings-based methods which are available only for a tiny fraction of the world’s languages. In this paper, we evaluate the performance of four widely used algorithms on the low-resource English-Yorùbá language pair against a multidomain benchmark parallel corpus on two experiments involving 1-to-1 alignments with and without reordering. We find that, at least for this language pair, earlier and simpler methods are more suited to the task, all the while not requiring additional data or resources. We also report that the methods we evaluated perform differently across distinct domains, thus indicating that some approach may be better for a specific domain or textual structure.
%R 10.18653/v1/2023.loresmt-1.10
%U https://aclanthology.org/2023.loresmt-1.10
%U https://doi.org/10.18653/v1/2023.loresmt-1.10
%P 123-129
Markdown (Informal)
[Evaluating Sentence Alignment Methods in a Low-Resource Setting: An English-YorùBá Study Case](https://aclanthology.org/2023.loresmt-1.10) (Signoroni & Rychlý, LoResMT 2023)
ACL