@inproceedings{fradet-etal-2023-byte,
title = "Byte Pair Encoding for Symbolic Music",
author = "Fradet, Nathan and
Gutowski, Nicolas and
Chhel, Fabien and
Briot, Jean-Pierre",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.123",
doi = "10.18653/v1/2023.emnlp-main.123",
pages = "2001--2020",
abstract = "When used with deep learning, the symbolic music modality is often coupled with language model architectures. To do so, the music needs to be tokenized, i.e. converted into a sequence of discrete tokens. This can be achieved by different approaches, as music can be composed of simultaneous tracks, of simultaneous notes with several attributes. Until now, the proposed tokenizations rely on small vocabularies of tokens describing the note attributes and time events, resulting in fairly long token sequences, and a sub-optimal use of the embedding space of language models. Recent research has put efforts on reducing the overall sequence length by merging embeddings or combining tokens. In this paper, we show that Byte Pair Encoding, a compression technique widely used for natural language, significantly decreases the sequence length while increasing the vocabulary size. By doing so, we leverage the embedding capabilities of such models with more expressive tokens, resulting in both better results and faster inference in generation and classification tasks. The [source code is shared on Github](https://github.com/Natooz/bpe-symbolic-music), along with a [companion website](https://Natooz.github.io/BPE-Symbolic-Music). Finally, BPE is directly implemented in [MidiTok](https://github.com/Natooz/MidiTok), allowing the reader to easily benefit from this method.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fradet-etal-2023-byte">
<titleInfo>
<title>Byte Pair Encoding for Symbolic Music</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Fradet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Gutowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabien</namePart>
<namePart type="family">Chhel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean-Pierre</namePart>
<namePart type="family">Briot</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>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</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>When used with deep learning, the symbolic music modality is often coupled with language model architectures. To do so, the music needs to be tokenized, i.e. converted into a sequence of discrete tokens. This can be achieved by different approaches, as music can be composed of simultaneous tracks, of simultaneous notes with several attributes. Until now, the proposed tokenizations rely on small vocabularies of tokens describing the note attributes and time events, resulting in fairly long token sequences, and a sub-optimal use of the embedding space of language models. Recent research has put efforts on reducing the overall sequence length by merging embeddings or combining tokens. In this paper, we show that Byte Pair Encoding, a compression technique widely used for natural language, significantly decreases the sequence length while increasing the vocabulary size. By doing so, we leverage the embedding capabilities of such models with more expressive tokens, resulting in both better results and faster inference in generation and classification tasks. The [source code is shared on Github](https://github.com/Natooz/bpe-symbolic-music), along with a [companion website](https://Natooz.github.io/BPE-Symbolic-Music). Finally, BPE is directly implemented in [MidiTok](https://github.com/Natooz/MidiTok), allowing the reader to easily benefit from this method.</abstract>
<identifier type="citekey">fradet-etal-2023-byte</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.123</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.123</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>2001</start>
<end>2020</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Byte Pair Encoding for Symbolic Music
%A Fradet, Nathan
%A Gutowski, Nicolas
%A Chhel, Fabien
%A Briot, Jean-Pierre
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F fradet-etal-2023-byte
%X When used with deep learning, the symbolic music modality is often coupled with language model architectures. To do so, the music needs to be tokenized, i.e. converted into a sequence of discrete tokens. This can be achieved by different approaches, as music can be composed of simultaneous tracks, of simultaneous notes with several attributes. Until now, the proposed tokenizations rely on small vocabularies of tokens describing the note attributes and time events, resulting in fairly long token sequences, and a sub-optimal use of the embedding space of language models. Recent research has put efforts on reducing the overall sequence length by merging embeddings or combining tokens. In this paper, we show that Byte Pair Encoding, a compression technique widely used for natural language, significantly decreases the sequence length while increasing the vocabulary size. By doing so, we leverage the embedding capabilities of such models with more expressive tokens, resulting in both better results and faster inference in generation and classification tasks. The [source code is shared on Github](https://github.com/Natooz/bpe-symbolic-music), along with a [companion website](https://Natooz.github.io/BPE-Symbolic-Music). Finally, BPE is directly implemented in [MidiTok](https://github.com/Natooz/MidiTok), allowing the reader to easily benefit from this method.
%R 10.18653/v1/2023.emnlp-main.123
%U https://aclanthology.org/2023.emnlp-main.123
%U https://doi.org/10.18653/v1/2023.emnlp-main.123
%P 2001-2020
Markdown (Informal)
[Byte Pair Encoding for Symbolic Music](https://aclanthology.org/2023.emnlp-main.123) (Fradet et al., EMNLP 2023)
ACL
- Nathan Fradet, Nicolas Gutowski, Fabien Chhel, and Jean-Pierre Briot. 2023. Byte Pair Encoding for Symbolic Music. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 2001–2020, Singapore. Association for Computational Linguistics.