@inproceedings{uthus-etal-2023-mlongt5,
title = "m{L}ong{T}5: A Multilingual and Efficient Text-To-Text Transformer for Longer Sequences",
author = "Uthus, David and
Ontanon, Santiago and
Ainslie, Joshua and
Guo, Mandy",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.628",
doi = "10.18653/v1/2023.findings-emnlp.628",
pages = "9380--9386",
abstract = "We present our work on developing a multilingual, efficient text-to-text transformer that is suitable for handling long inputs. This model, called mLongT5, builds upon the architecture of LongT5, while leveraging the multilingual datasets used for pretraining mT5 and the pretraining tasks of UL2. We evaluate this model on a variety of multilingual summarization and question-answering tasks, and the results show stronger performance for mLongT5 when compared to existing multilingual models such as mBART or M-BERT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="uthus-etal-2023-mlongt5">
<titleInfo>
<title>mLongT5: A Multilingual and Efficient Text-To-Text Transformer for Longer Sequences</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Uthus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Santiago</namePart>
<namePart type="family">Ontanon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="family">Ainslie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mandy</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present our work on developing a multilingual, efficient text-to-text transformer that is suitable for handling long inputs. This model, called mLongT5, builds upon the architecture of LongT5, while leveraging the multilingual datasets used for pretraining mT5 and the pretraining tasks of UL2. We evaluate this model on a variety of multilingual summarization and question-answering tasks, and the results show stronger performance for mLongT5 when compared to existing multilingual models such as mBART or M-BERT.</abstract>
<identifier type="citekey">uthus-etal-2023-mlongt5</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.628</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.628</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>9380</start>
<end>9386</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T mLongT5: A Multilingual and Efficient Text-To-Text Transformer for Longer Sequences
%A Uthus, David
%A Ontanon, Santiago
%A Ainslie, Joshua
%A Guo, Mandy
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F uthus-etal-2023-mlongt5
%X We present our work on developing a multilingual, efficient text-to-text transformer that is suitable for handling long inputs. This model, called mLongT5, builds upon the architecture of LongT5, while leveraging the multilingual datasets used for pretraining mT5 and the pretraining tasks of UL2. We evaluate this model on a variety of multilingual summarization and question-answering tasks, and the results show stronger performance for mLongT5 when compared to existing multilingual models such as mBART or M-BERT.
%R 10.18653/v1/2023.findings-emnlp.628
%U https://aclanthology.org/2023.findings-emnlp.628
%U https://doi.org/10.18653/v1/2023.findings-emnlp.628
%P 9380-9386
Markdown (Informal)
[mLongT5: A Multilingual and Efficient Text-To-Text Transformer for Longer Sequences](https://aclanthology.org/2023.findings-emnlp.628) (Uthus et al., Findings 2023)
ACL