@inproceedings{han-etal-2022-examining,
title = "Examining Large Pre-Trained Language Models for Machine Translation: What You Don{'}t Know about It",
author = "Han, Lifeng and
Erofeev, Gleb and
Sorokina, Irina and
Gladkoff, Serge and
Nenadic, Goran",
editor = {Koehn, Philipp and
Barrault, Lo{\"\i}c and
Bojar, Ond{\v{r}}ej and
Bougares, Fethi and
Chatterjee, Rajen and
Costa-juss{\`a}, Marta R. and
Federmann, Christian and
Fishel, Mark and
Fraser, Alexander and
Freitag, Markus and
Graham, Yvette and
Grundkiewicz, Roman and
Guzman, Paco and
Haddow, Barry and
Huck, Matthias and
Jimeno Yepes, Antonio and
Kocmi, Tom and
Martins, Andr{\'e} and
Morishita, Makoto and
Monz, Christof and
Nagata, Masaaki and
Nakazawa, Toshiaki and
Negri, Matteo and
N{\'e}v{\'e}ol, Aur{\'e}lie and
Neves, Mariana and
Popel, Martin and
Turchi, Marco and
Zampieri, Marcos},
booktitle = "Proceedings of the Seventh Conference on Machine Translation (WMT)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.wmt-1.84",
pages = "908--919",
abstract = "Pre-trained language models (PLMs) often take advantage of the monolingual and multilingual dataset that is freely available online to acquire general or mixed domain knowledge before deployment into specific tasks. Extra-large PLMs (xLPLMs) are proposed very recently to claim supreme performances over smaller-sized PLMs such as in machine translation (MT) tasks. These xLPLMs include Meta-AI{'}s wmt21-dense-24-wide-en-X (2021) and NLLB (2022). In this work, we examine if xLPLMs are absolutely superior to smaller-sized PLMs in fine-tuning toward domain-specific MTs. We use two different in-domain data of different sizes: commercial automotive in-house data and clinical shared task data from the ClinSpEn2022 challenge at WMT2022. We choose the popular Marian Helsinki as smaller sized PLM and two massive-sized Mega-Transformers from Meta-AI as xLPLMs.Our experimental investigation shows that 1) on smaller-sized in-domain commercial automotive data, xLPLM wmt21-dense-24-wide-en-X indeed shows much better evaluation scores using SacreBLEU and hLEPOR metrics than smaller-sized Marian, even though its score increase rate is lower than Marian after fine-tuning; 2) on relatively larger-size well prepared clinical data fine-tuning, the xLPLM NLLB tends to lose its advantage over smaller-sized Marian on two sub-tasks (clinical terms and ontology concepts) using ClinSpEn offered metrics METEOR, COMET, and ROUGE-L, and totally lost to Marian on Task-1 (clinical cases) on all official metrics including SacreBLEU and BLEU; 3) metrics do not always agree with each other on the same tasks using the same model outputs; 4) clinic-Marian ranked No.2 on Task- 1 (via SacreBLEU/BLEU) and Task-3 (via METEOR and ROUGE) among all submissions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="han-etal-2022-examining">
<titleInfo>
<title>Examining Large Pre-Trained Language Models for Machine Translation: What You Don’t Know about It</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lifeng</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gleb</namePart>
<namePart type="family">Erofeev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Irina</namePart>
<namePart type="family">Sorokina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serge</namePart>
<namePart type="family">Gladkoff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Goran</namePart>
<namePart type="family">Nenadic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh Conference on Machine Translation (WMT)</title>
</titleInfo>
<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">Loïc</namePart>
<namePart type="family">Barrault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajen</namePart>
<namePart type="family">Chatterjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Federmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Fraser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Freitag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Grundkiewicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paco</namePart>
<namePart type="family">Guzman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Matthias</namePart>
<namePart type="family">Huck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Jimeno Yepes</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">André</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Morishita</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>
<name type="personal">
<namePart type="given">Masaaki</namePart>
<namePart type="family">Nagata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toshiaki</namePart>
<namePart type="family">Nakazawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aurélie</namePart>
<namePart type="family">Névéol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariana</namePart>
<namePart type="family">Neves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Popel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pre-trained language models (PLMs) often take advantage of the monolingual and multilingual dataset that is freely available online to acquire general or mixed domain knowledge before deployment into specific tasks. Extra-large PLMs (xLPLMs) are proposed very recently to claim supreme performances over smaller-sized PLMs such as in machine translation (MT) tasks. These xLPLMs include Meta-AI’s wmt21-dense-24-wide-en-X (2021) and NLLB (2022). In this work, we examine if xLPLMs are absolutely superior to smaller-sized PLMs in fine-tuning toward domain-specific MTs. We use two different in-domain data of different sizes: commercial automotive in-house data and clinical shared task data from the ClinSpEn2022 challenge at WMT2022. We choose the popular Marian Helsinki as smaller sized PLM and two massive-sized Mega-Transformers from Meta-AI as xLPLMs.Our experimental investigation shows that 1) on smaller-sized in-domain commercial automotive data, xLPLM wmt21-dense-24-wide-en-X indeed shows much better evaluation scores using SacreBLEU and hLEPOR metrics than smaller-sized Marian, even though its score increase rate is lower than Marian after fine-tuning; 2) on relatively larger-size well prepared clinical data fine-tuning, the xLPLM NLLB tends to lose its advantage over smaller-sized Marian on two sub-tasks (clinical terms and ontology concepts) using ClinSpEn offered metrics METEOR, COMET, and ROUGE-L, and totally lost to Marian on Task-1 (clinical cases) on all official metrics including SacreBLEU and BLEU; 3) metrics do not always agree with each other on the same tasks using the same model outputs; 4) clinic-Marian ranked No.2 on Task- 1 (via SacreBLEU/BLEU) and Task-3 (via METEOR and ROUGE) among all submissions.</abstract>
<identifier type="citekey">han-etal-2022-examining</identifier>
<location>
<url>https://aclanthology.org/2022.wmt-1.84</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>908</start>
<end>919</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Examining Large Pre-Trained Language Models for Machine Translation: What You Don’t Know about It
%A Han, Lifeng
%A Erofeev, Gleb
%A Sorokina, Irina
%A Gladkoff, Serge
%A Nenadic, Goran
%Y Koehn, Philipp
%Y Barrault, Loïc
%Y Bojar, Ondřej
%Y Bougares, Fethi
%Y Chatterjee, Rajen
%Y Costa-jussà, Marta R.
%Y Federmann, Christian
%Y Fishel, Mark
%Y Fraser, Alexander
%Y Freitag, Markus
%Y Graham, Yvette
%Y Grundkiewicz, Roman
%Y Guzman, Paco
%Y Haddow, Barry
%Y Huck, Matthias
%Y Jimeno Yepes, Antonio
%Y Kocmi, Tom
%Y Martins, André
%Y Morishita, Makoto
%Y Monz, Christof
%Y Nagata, Masaaki
%Y Nakazawa, Toshiaki
%Y Negri, Matteo
%Y Névéol, Aurélie
%Y Neves, Mariana
%Y Popel, Martin
%Y Turchi, Marco
%Y Zampieri, Marcos
%S Proceedings of the Seventh Conference on Machine Translation (WMT)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F han-etal-2022-examining
%X Pre-trained language models (PLMs) often take advantage of the monolingual and multilingual dataset that is freely available online to acquire general or mixed domain knowledge before deployment into specific tasks. Extra-large PLMs (xLPLMs) are proposed very recently to claim supreme performances over smaller-sized PLMs such as in machine translation (MT) tasks. These xLPLMs include Meta-AI’s wmt21-dense-24-wide-en-X (2021) and NLLB (2022). In this work, we examine if xLPLMs are absolutely superior to smaller-sized PLMs in fine-tuning toward domain-specific MTs. We use two different in-domain data of different sizes: commercial automotive in-house data and clinical shared task data from the ClinSpEn2022 challenge at WMT2022. We choose the popular Marian Helsinki as smaller sized PLM and two massive-sized Mega-Transformers from Meta-AI as xLPLMs.Our experimental investigation shows that 1) on smaller-sized in-domain commercial automotive data, xLPLM wmt21-dense-24-wide-en-X indeed shows much better evaluation scores using SacreBLEU and hLEPOR metrics than smaller-sized Marian, even though its score increase rate is lower than Marian after fine-tuning; 2) on relatively larger-size well prepared clinical data fine-tuning, the xLPLM NLLB tends to lose its advantage over smaller-sized Marian on two sub-tasks (clinical terms and ontology concepts) using ClinSpEn offered metrics METEOR, COMET, and ROUGE-L, and totally lost to Marian on Task-1 (clinical cases) on all official metrics including SacreBLEU and BLEU; 3) metrics do not always agree with each other on the same tasks using the same model outputs; 4) clinic-Marian ranked No.2 on Task- 1 (via SacreBLEU/BLEU) and Task-3 (via METEOR and ROUGE) among all submissions.
%U https://aclanthology.org/2022.wmt-1.84
%P 908-919
Markdown (Informal)
[Examining Large Pre-Trained Language Models for Machine Translation: What You Don’t Know about It](https://aclanthology.org/2022.wmt-1.84) (Han et al., WMT 2022)
ACL