@inproceedings{riabi-etal-2021-character,
title = "Can Character-based Language Models Improve Downstream Task Performances In Low-Resource And Noisy Language Scenarios?",
author = "Riabi, Arij and
Sagot, Beno{\^\i}t and
Seddah, Djam{\'e}",
editor = "Xu, Wei and
Ritter, Alan and
Baldwin, Tim and
Rahimi, Afshin",
booktitle = "Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)",
month = nov,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wnut-1.47",
doi = "10.18653/v1/2021.wnut-1.47",
pages = "423--436",
abstract = "Recent impressive improvements in NLP, largely based on the success of contextual neural language models, have been mostly demonstrated on at most a couple dozen high- resource languages. Building language mod- els and, more generally, NLP systems for non- standardized and low-resource languages remains a challenging task. In this work, we fo- cus on North-African colloquial dialectal Arabic written using an extension of the Latin script, called NArabizi, found mostly on social media and messaging communication. In this low-resource scenario with data display- ing a high level of variability, we compare the downstream performance of a character-based language model on part-of-speech tagging and dependency parsing to that of monolingual and multilingual models. We show that a character-based model trained on only 99k sentences of NArabizi and fined-tuned on a small treebank of this language leads to performance close to those obtained with the same architecture pre- trained on large multilingual and monolingual models. Confirming these results a on much larger data set of noisy French user-generated content, we argue that such character-based language models can be an asset for NLP in low-resource and high language variability set- tings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="riabi-etal-2021-character">
<titleInfo>
<title>Can Character-based Language Models Improve Downstream Task Performances In Low-Resource And Noisy Language Scenarios?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arij</namePart>
<namePart type="family">Riabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benoît</namePart>
<namePart type="family">Sagot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Djamé</namePart>
<namePart type="family">Seddah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afshin</namePart>
<namePart type="family">Rahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent impressive improvements in NLP, largely based on the success of contextual neural language models, have been mostly demonstrated on at most a couple dozen high- resource languages. Building language mod- els and, more generally, NLP systems for non- standardized and low-resource languages remains a challenging task. In this work, we fo- cus on North-African colloquial dialectal Arabic written using an extension of the Latin script, called NArabizi, found mostly on social media and messaging communication. In this low-resource scenario with data display- ing a high level of variability, we compare the downstream performance of a character-based language model on part-of-speech tagging and dependency parsing to that of monolingual and multilingual models. We show that a character-based model trained on only 99k sentences of NArabizi and fined-tuned on a small treebank of this language leads to performance close to those obtained with the same architecture pre- trained on large multilingual and monolingual models. Confirming these results a on much larger data set of noisy French user-generated content, we argue that such character-based language models can be an asset for NLP in low-resource and high language variability set- tings.</abstract>
<identifier type="citekey">riabi-etal-2021-character</identifier>
<identifier type="doi">10.18653/v1/2021.wnut-1.47</identifier>
<location>
<url>https://aclanthology.org/2021.wnut-1.47</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>423</start>
<end>436</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can Character-based Language Models Improve Downstream Task Performances In Low-Resource And Noisy Language Scenarios?
%A Riabi, Arij
%A Sagot, Benoît
%A Seddah, Djamé
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%Y Rahimi, Afshin
%S Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online
%F riabi-etal-2021-character
%X Recent impressive improvements in NLP, largely based on the success of contextual neural language models, have been mostly demonstrated on at most a couple dozen high- resource languages. Building language mod- els and, more generally, NLP systems for non- standardized and low-resource languages remains a challenging task. In this work, we fo- cus on North-African colloquial dialectal Arabic written using an extension of the Latin script, called NArabizi, found mostly on social media and messaging communication. In this low-resource scenario with data display- ing a high level of variability, we compare the downstream performance of a character-based language model on part-of-speech tagging and dependency parsing to that of monolingual and multilingual models. We show that a character-based model trained on only 99k sentences of NArabizi and fined-tuned on a small treebank of this language leads to performance close to those obtained with the same architecture pre- trained on large multilingual and monolingual models. Confirming these results a on much larger data set of noisy French user-generated content, we argue that such character-based language models can be an asset for NLP in low-resource and high language variability set- tings.
%R 10.18653/v1/2021.wnut-1.47
%U https://aclanthology.org/2021.wnut-1.47
%U https://doi.org/10.18653/v1/2021.wnut-1.47
%P 423-436
Markdown (Informal)
[Can Character-based Language Models Improve Downstream Task Performances In Low-Resource And Noisy Language Scenarios?](https://aclanthology.org/2021.wnut-1.47) (Riabi et al., WNUT 2021)
ACL