@inproceedings{avramidis-etal-2024-occiglot,
title = "Occiglot at {WMT}24: {E}uropean Open-source Large Language Models Evaluated on Translation",
author = {Avramidis, Eleftherios and
Gr{\"u}tzner-Zahn, Annika and
Brack, Manuel and
Schramowski, Patrick and
Ortiz Suarez, Pedro and
Ostendorff, Malte and
Barth, Fabio and
Manakhimova, Shushen and
Macketanz, Vivien and
Rehm, Georg and
Kersting, Kristian},
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-1.23",
doi = "10.18653/v1/2024.wmt-1.23",
pages = "292--298",
abstract = "This document describes the submission of the very first version of the Occiglot open-source large language model to the General MT Shared Task of the 9th Conference of Machine Translation (WMT24). Occiglot is an open-source, community-based LLM based on Mistral-7B, which went through language-specific continual pre-training and subsequent instruction tuning, including instructions relevant to machine translation.We examine the automatic metric scores for translating the WMT24 test set and provide a detailed linguistically-motivated analysis.Despite Occiglot performing worse than many of the other system submissions, we observe that it performs better than Mistral7B, which has been based upon, which indicates the positive effect of the language specific continual-pretraining and instruction tuning. We see the submission of this very early version of the model as a motivation to unite community forces and pursue future LLM research on the translation task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="avramidis-etal-2024-occiglot">
<titleInfo>
<title>Occiglot at WMT24: European Open-source Large Language Models Evaluated on Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eleftherios</namePart>
<namePart type="family">Avramidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annika</namePart>
<namePart type="family">Grützner-Zahn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="family">Brack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Schramowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="family">Ortiz Suarez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malte</namePart>
<namePart type="family">Ostendorff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Barth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shushen</namePart>
<namePart type="family">Manakhimova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivien</namePart>
<namePart type="family">Macketanz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristian</namePart>
<namePart type="family">Kersting</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 document describes the submission of the very first version of the Occiglot open-source large language model to the General MT Shared Task of the 9th Conference of Machine Translation (WMT24). Occiglot is an open-source, community-based LLM based on Mistral-7B, which went through language-specific continual pre-training and subsequent instruction tuning, including instructions relevant to machine translation.We examine the automatic metric scores for translating the WMT24 test set and provide a detailed linguistically-motivated analysis.Despite Occiglot performing worse than many of the other system submissions, we observe that it performs better than Mistral7B, which has been based upon, which indicates the positive effect of the language specific continual-pretraining and instruction tuning. We see the submission of this very early version of the model as a motivation to unite community forces and pursue future LLM research on the translation task.</abstract>
<identifier type="citekey">avramidis-etal-2024-occiglot</identifier>
<identifier type="doi">10.18653/v1/2024.wmt-1.23</identifier>
<location>
<url>https://aclanthology.org/2024.wmt-1.23</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>292</start>
<end>298</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Occiglot at WMT24: European Open-source Large Language Models Evaluated on Translation
%A Avramidis, Eleftherios
%A Grützner-Zahn, Annika
%A Brack, Manuel
%A Schramowski, Patrick
%A Ortiz Suarez, Pedro
%A Ostendorff, Malte
%A Barth, Fabio
%A Manakhimova, Shushen
%A Macketanz, Vivien
%A Rehm, Georg
%A Kersting, Kristian
%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 avramidis-etal-2024-occiglot
%X This document describes the submission of the very first version of the Occiglot open-source large language model to the General MT Shared Task of the 9th Conference of Machine Translation (WMT24). Occiglot is an open-source, community-based LLM based on Mistral-7B, which went through language-specific continual pre-training and subsequent instruction tuning, including instructions relevant to machine translation.We examine the automatic metric scores for translating the WMT24 test set and provide a detailed linguistically-motivated analysis.Despite Occiglot performing worse than many of the other system submissions, we observe that it performs better than Mistral7B, which has been based upon, which indicates the positive effect of the language specific continual-pretraining and instruction tuning. We see the submission of this very early version of the model as a motivation to unite community forces and pursue future LLM research on the translation task.
%R 10.18653/v1/2024.wmt-1.23
%U https://aclanthology.org/2024.wmt-1.23
%U https://doi.org/10.18653/v1/2024.wmt-1.23
%P 292-298
Markdown (Informal)
[Occiglot at WMT24: European Open-source Large Language Models Evaluated on Translation](https://aclanthology.org/2024.wmt-1.23) (Avramidis et al., WMT 2024)
ACL
- Eleftherios Avramidis, Annika Grützner-Zahn, Manuel Brack, Patrick Schramowski, Pedro Ortiz Suarez, Malte Ostendorff, Fabio Barth, Shushen Manakhimova, Vivien Macketanz, Georg Rehm, and Kristian Kersting. 2024. Occiglot at WMT24: European Open-source Large Language Models Evaluated on Translation. In Proceedings of the Ninth Conference on Machine Translation, pages 292–298, Miami, Florida, USA. Association for Computational Linguistics.