@inproceedings{han-etal-2023-investigating,
title = "Investigating Massive Multilingual Pre-Trained Machine Translation Models for Clinical Domain via Transfer Learning",
author = "Han, Lifeng and
Erofeev, Gleb and
Sorokina, Irina and
Gladkoff, Serge and
Nenadic, Goran",
editor = "Naumann, Tristan and
Ben Abacha, Asma and
Bethard, Steven and
Roberts, Kirk and
Rumshisky, Anna",
booktitle = "Proceedings of the 5th Clinical Natural Language Processing Workshop",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.clinicalnlp-1.5",
doi = "10.18653/v1/2023.clinicalnlp-1.5",
pages = "31--40",
abstract = "Massively multilingual pre-trained language models (MMPLMs) are developed in recent years demonstrating superpowers and the pre-knowledge they acquire for downstream tasks. This work investigates whether MMPLMs can be applied to clinical domain machine translation (MT) towards entirely unseen languages via transfer learning. We carry out an experimental investigation using Meta-AI{'}s MMPLMs {``}wmt21-dense-24-wide-en-X and X-en (WMT21fb){''} which were pre-trained on 7 language pairs and 14 translation directions including English to Czech, German, Hausa, Icelandic, Japanese, Russian, and Chinese, and the opposite direction. We fine-tune these MMPLMs towards English-\textit{Spanish} language pair which \textit{did not exist at all} in their original pre-trained corpora both implicitly and explicitly.We prepare carefully aligned \textit{clinical} domain data for this fine-tuning, which is different from their original mixed domain knowledge.Our experimental result shows that the fine-tuning is very successful using just 250k well-aligned in-domain EN-ES segments for three sub-task translation testings: clinical cases, clinical terms, and ontology concepts. It achieves very close evaluation scores to another MMPLM NLLB from Meta-AI, which included Spanish as a high-resource setting in the pre-training.To the best of our knowledge, this is the first work on using MMPLMs towards \textit{clinical domain transfer-learning NMT} successfully for totally unseen languages during pre-training.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="han-etal-2023-investigating">
<titleInfo>
<title>Investigating Massive Multilingual Pre-Trained Machine Translation Models for Clinical Domain via Transfer Learning</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>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Clinical Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Naumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="family">Ben Abacha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Massively multilingual pre-trained language models (MMPLMs) are developed in recent years demonstrating superpowers and the pre-knowledge they acquire for downstream tasks. This work investigates whether MMPLMs can be applied to clinical domain machine translation (MT) towards entirely unseen languages via transfer learning. We carry out an experimental investigation using Meta-AI’s MMPLMs “wmt21-dense-24-wide-en-X and X-en (WMT21fb)” which were pre-trained on 7 language pairs and 14 translation directions including English to Czech, German, Hausa, Icelandic, Japanese, Russian, and Chinese, and the opposite direction. We fine-tune these MMPLMs towards English-Spanish language pair which did not exist at all in their original pre-trained corpora both implicitly and explicitly.We prepare carefully aligned clinical domain data for this fine-tuning, which is different from their original mixed domain knowledge.Our experimental result shows that the fine-tuning is very successful using just 250k well-aligned in-domain EN-ES segments for three sub-task translation testings: clinical cases, clinical terms, and ontology concepts. It achieves very close evaluation scores to another MMPLM NLLB from Meta-AI, which included Spanish as a high-resource setting in the pre-training.To the best of our knowledge, this is the first work on using MMPLMs towards clinical domain transfer-learning NMT successfully for totally unseen languages during pre-training.</abstract>
<identifier type="citekey">han-etal-2023-investigating</identifier>
<identifier type="doi">10.18653/v1/2023.clinicalnlp-1.5</identifier>
<location>
<url>https://aclanthology.org/2023.clinicalnlp-1.5</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>31</start>
<end>40</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigating Massive Multilingual Pre-Trained Machine Translation Models for Clinical Domain via Transfer Learning
%A Han, Lifeng
%A Erofeev, Gleb
%A Sorokina, Irina
%A Gladkoff, Serge
%A Nenadic, Goran
%Y Naumann, Tristan
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Roberts, Kirk
%Y Rumshisky, Anna
%S Proceedings of the 5th Clinical Natural Language Processing Workshop
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F han-etal-2023-investigating
%X Massively multilingual pre-trained language models (MMPLMs) are developed in recent years demonstrating superpowers and the pre-knowledge they acquire for downstream tasks. This work investigates whether MMPLMs can be applied to clinical domain machine translation (MT) towards entirely unseen languages via transfer learning. We carry out an experimental investigation using Meta-AI’s MMPLMs “wmt21-dense-24-wide-en-X and X-en (WMT21fb)” which were pre-trained on 7 language pairs and 14 translation directions including English to Czech, German, Hausa, Icelandic, Japanese, Russian, and Chinese, and the opposite direction. We fine-tune these MMPLMs towards English-Spanish language pair which did not exist at all in their original pre-trained corpora both implicitly and explicitly.We prepare carefully aligned clinical domain data for this fine-tuning, which is different from their original mixed domain knowledge.Our experimental result shows that the fine-tuning is very successful using just 250k well-aligned in-domain EN-ES segments for three sub-task translation testings: clinical cases, clinical terms, and ontology concepts. It achieves very close evaluation scores to another MMPLM NLLB from Meta-AI, which included Spanish as a high-resource setting in the pre-training.To the best of our knowledge, this is the first work on using MMPLMs towards clinical domain transfer-learning NMT successfully for totally unseen languages during pre-training.
%R 10.18653/v1/2023.clinicalnlp-1.5
%U https://aclanthology.org/2023.clinicalnlp-1.5
%U https://doi.org/10.18653/v1/2023.clinicalnlp-1.5
%P 31-40
Markdown (Informal)
[Investigating Massive Multilingual Pre-Trained Machine Translation Models for Clinical Domain via Transfer Learning](https://aclanthology.org/2023.clinicalnlp-1.5) (Han et al., ClinicalNLP 2023)
ACL