<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chizhov-etal-2024-bpe">
    <titleInfo>
        <title>BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Pavel</namePart>
        <namePart type="family">Chizhov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Catherine</namePart>
        <namePart type="family">Arnett</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Elizaveta</namePart>
        <namePart type="family">Korotkova</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ivan</namePart>
        <namePart type="family">Yamshchikov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yaser</namePart>
            <namePart type="family">Al-Onaizan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yun-Nung</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Language models can greatly benefit from efficient tokenization. However, they still mostly utilize the classical Byte-Pair Encoding (BPE) algorithm, a simple and reliable method. BPE has been shown to cause such issues as under-trained tokens and sub-optimal compression that may affect the downstream performance. We introduce PickyBPE, a modified BPE algorithm that carries out vocabulary refinement during tokenizer training by removing merges that leave intermediate “junk” tokens. Our method improves vocabulary efficiency, eliminates under-trained tokens, and does not compromise text compression. Our experiments show that this method either improves downstream performance or does not harm it.</abstract>
    <identifier type="citekey">chizhov-etal-2024-bpe</identifier>
    <location>
        <url>https://aclanthology.org/2024.emnlp-main.925</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>16587</start>
            <end>16604</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training
%A Chizhov, Pavel
%A Arnett, Catherine
%A Korotkova, Elizaveta
%A Yamshchikov, Ivan
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F chizhov-etal-2024-bpe
%X Language models can greatly benefit from efficient tokenization. However, they still mostly utilize the classical Byte-Pair Encoding (BPE) algorithm, a simple and reliable method. BPE has been shown to cause such issues as under-trained tokens and sub-optimal compression that may affect the downstream performance. We introduce PickyBPE, a modified BPE algorithm that carries out vocabulary refinement during tokenizer training by removing merges that leave intermediate “junk” tokens. Our method improves vocabulary efficiency, eliminates under-trained tokens, and does not compromise text compression. Our experiments show that this method either improves downstream performance or does not harm it.
%U https://aclanthology.org/2024.emnlp-main.925
%P 16587-16604

Markdown (Informal)

[BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training](https://aclanthology.org/2024.emnlp-main.925) (Chizhov et al., EMNLP 2024)

• BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training (Chizhov et al., EMNLP 2024)

ACL

• Pavel Chizhov, Catherine Arnett, Elizaveta Korotkova, and Ivan Yamshchikov. 2024. BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 16587–16604, Miami, Florida, USA. Association for Computational Linguistics.