@inproceedings{velasco-etal-2024-samsung,
title = "{S}amsung {R}{\&}{D} Institute {P}hilippines @ {WMT} 2024 Low-resource Languages of {S}pain Shared Task",
author = "Velasco, Dan John and
Rufino, Manuel Antonio and
Cruz, Jan Christian Blaise",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Ninth Conference on Machine Translation",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.wmt-1.86",
pages = "892--900",
abstract = "This paper details the submission of Samsung R{\&}D Institute Philippines (SRPH) Language Intelligence Team (LIT) to the WMT 2024 Low-resource Languages of Spain shared task. We trained translation models for Spanish to Aragonese, Spanish to Aranese/Occitan, and Spanish to Asturian using a standard sequence-to-sequence Transformer architecture, augmenting it with a noisy-channel reranking strategy to select better outputs during decoding. For Spanish to Asturian translation, our method reaches comparable BLEU scores to a strong commercial baseline translation system using only constrained data, backtranslations, noisy channel reranking, and a shared vocabulary spanning all four languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="velasco-etal-2024-samsung">
<titleInfo>
<title>Samsung R&D Institute Philippines @ WMT 2024 Low-resource Languages of Spain Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="given">John</namePart>
<namePart type="family">Velasco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="given">Antonio</namePart>
<namePart type="family">Rufino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="given">Christian</namePart>
<namePart type="given">Blaise</namePart>
<namePart type="family">Cruz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper details the submission of Samsung R&D Institute Philippines (SRPH) Language Intelligence Team (LIT) to the WMT 2024 Low-resource Languages of Spain shared task. We trained translation models for Spanish to Aragonese, Spanish to Aranese/Occitan, and Spanish to Asturian using a standard sequence-to-sequence Transformer architecture, augmenting it with a noisy-channel reranking strategy to select better outputs during decoding. For Spanish to Asturian translation, our method reaches comparable BLEU scores to a strong commercial baseline translation system using only constrained data, backtranslations, noisy channel reranking, and a shared vocabulary spanning all four languages.</abstract>
<identifier type="citekey">velasco-etal-2024-samsung</identifier>
<location>
<url>https://aclanthology.org/2024.wmt-1.86</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>892</start>
<end>900</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Samsung R&D Institute Philippines @ WMT 2024 Low-resource Languages of Spain Shared Task
%A Velasco, Dan John
%A Rufino, Manuel Antonio
%A Cruz, Jan Christian Blaise
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Ninth Conference on Machine Translation
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F velasco-etal-2024-samsung
%X This paper details the submission of Samsung R&D Institute Philippines (SRPH) Language Intelligence Team (LIT) to the WMT 2024 Low-resource Languages of Spain shared task. We trained translation models for Spanish to Aragonese, Spanish to Aranese/Occitan, and Spanish to Asturian using a standard sequence-to-sequence Transformer architecture, augmenting it with a noisy-channel reranking strategy to select better outputs during decoding. For Spanish to Asturian translation, our method reaches comparable BLEU scores to a strong commercial baseline translation system using only constrained data, backtranslations, noisy channel reranking, and a shared vocabulary spanning all four languages.
%U https://aclanthology.org/2024.wmt-1.86
%P 892-900
Markdown (Informal)
[Samsung R&D Institute Philippines @ WMT 2024 Low-resource Languages of Spain Shared Task](https://aclanthology.org/2024.wmt-1.86) (Velasco et al., WMT 2024)
ACL