@inproceedings{samuel-ovrelid-2023-tokenization,
title = "Tokenization with Factorized Subword Encoding",
author = "Samuel, David and
{\O}vrelid, Lilja",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.890",
doi = "10.18653/v1/2023.findings-acl.890",
pages = "14143--14161",
abstract = "In recent years, language models have become increasingly larger and more complex. However, the input representations for these models continue to rely on simple and greedy subword tokenization methods. In this paper, we propose a novel tokenization method that factorizes subwords onto discrete triplets using a VQ-VAE model. The effectiveness of the proposed tokenization method, referred to as the Factorizer, is evaluated on language modeling and morpho-syntactic tasks for 7 diverse languages. Results indicate that this method is more appropriate and robust for morphological tasks than the commonly used byte-pair encoding (BPE) tokenization algorithm.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="samuel-ovrelid-2023-tokenization">
<titleInfo>
<title>Tokenization with Factorized Subword Encoding</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Samuel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilja</namePart>
<namePart type="family">Øvrelid</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>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</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>In recent years, language models have become increasingly larger and more complex. However, the input representations for these models continue to rely on simple and greedy subword tokenization methods. In this paper, we propose a novel tokenization method that factorizes subwords onto discrete triplets using a VQ-VAE model. The effectiveness of the proposed tokenization method, referred to as the Factorizer, is evaluated on language modeling and morpho-syntactic tasks for 7 diverse languages. Results indicate that this method is more appropriate and robust for morphological tasks than the commonly used byte-pair encoding (BPE) tokenization algorithm.</abstract>
<identifier type="citekey">samuel-ovrelid-2023-tokenization</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.890</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.890</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>14143</start>
<end>14161</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tokenization with Factorized Subword Encoding
%A Samuel, David
%A Øvrelid, Lilja
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F samuel-ovrelid-2023-tokenization
%X In recent years, language models have become increasingly larger and more complex. However, the input representations for these models continue to rely on simple and greedy subword tokenization methods. In this paper, we propose a novel tokenization method that factorizes subwords onto discrete triplets using a VQ-VAE model. The effectiveness of the proposed tokenization method, referred to as the Factorizer, is evaluated on language modeling and morpho-syntactic tasks for 7 diverse languages. Results indicate that this method is more appropriate and robust for morphological tasks than the commonly used byte-pair encoding (BPE) tokenization algorithm.
%R 10.18653/v1/2023.findings-acl.890
%U https://aclanthology.org/2023.findings-acl.890
%U https://doi.org/10.18653/v1/2023.findings-acl.890
%P 14143-14161
Markdown (Informal)
[Tokenization with Factorized Subword Encoding](https://aclanthology.org/2023.findings-acl.890) (Samuel & Øvrelid, Findings 2023)
ACL
- David Samuel and Lilja Øvrelid. 2023. Tokenization with Factorized Subword Encoding. In Findings of the Association for Computational Linguistics: ACL 2023, pages 14143–14161, Toronto, Canada. Association for Computational Linguistics.