@inproceedings{leong-whitenack-2022-phone,
title = "Phone-ing it in: Towards Flexible Multi-Modal Language Model Training by Phonetic Representations of Data",
author = "Leong, Colin and
Whitenack, Daniel",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.364",
doi = "10.18653/v1/2022.acl-long.364",
pages = "5306--5315",
abstract = "Multi-modal techniques offer significant untapped potential to unlock improved NLP technology for local languages. However, many advances in language model pre-training are focused on text, a fact that only increases systematic inequalities in the performance of NLP tasks across the world{'}s languages. In this work, we propose a multi-modal approach to train language models using whatever text and/or audio data might be available in a language. Initial experiments using Swahili and Kinyarwanda data suggest the viability of the approach for downstream Named Entity Recognition (NER) tasks, with models pre-trained on phone data showing an improvement of up to 6{\%} F1-score above models that are trained from scratch. Preprocessing and training code will be uploaded to \url{https://github.com/sil-ai/phone-it-in}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="leong-whitenack-2022-phone">
<titleInfo>
<title>Phone-ing it in: Towards Flexible Multi-Modal Language Model Training by Phonetic Representations of Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Colin</namePart>
<namePart type="family">Leong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Whitenack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multi-modal techniques offer significant untapped potential to unlock improved NLP technology for local languages. However, many advances in language model pre-training are focused on text, a fact that only increases systematic inequalities in the performance of NLP tasks across the world’s languages. In this work, we propose a multi-modal approach to train language models using whatever text and/or audio data might be available in a language. Initial experiments using Swahili and Kinyarwanda data suggest the viability of the approach for downstream Named Entity Recognition (NER) tasks, with models pre-trained on phone data showing an improvement of up to 6% F1-score above models that are trained from scratch. Preprocessing and training code will be uploaded to https://github.com/sil-ai/phone-it-in.</abstract>
<identifier type="citekey">leong-whitenack-2022-phone</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.364</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.364</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>5306</start>
<end>5315</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Phone-ing it in: Towards Flexible Multi-Modal Language Model Training by Phonetic Representations of Data
%A Leong, Colin
%A Whitenack, Daniel
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F leong-whitenack-2022-phone
%X Multi-modal techniques offer significant untapped potential to unlock improved NLP technology for local languages. However, many advances in language model pre-training are focused on text, a fact that only increases systematic inequalities in the performance of NLP tasks across the world’s languages. In this work, we propose a multi-modal approach to train language models using whatever text and/or audio data might be available in a language. Initial experiments using Swahili and Kinyarwanda data suggest the viability of the approach for downstream Named Entity Recognition (NER) tasks, with models pre-trained on phone data showing an improvement of up to 6% F1-score above models that are trained from scratch. Preprocessing and training code will be uploaded to https://github.com/sil-ai/phone-it-in.
%R 10.18653/v1/2022.acl-long.364
%U https://aclanthology.org/2022.acl-long.364
%U https://doi.org/10.18653/v1/2022.acl-long.364
%P 5306-5315
Markdown (Informal)
[Phone-ing it in: Towards Flexible Multi-Modal Language Model Training by Phonetic Representations of Data](https://aclanthology.org/2022.acl-long.364) (Leong & Whitenack, ACL 2022)
ACL