@inproceedings{zhang-etal-2024-syllable,
title = "Syllable-level lyrics generation from melody exploiting character-level language model",
author = "Zhang, Zhe and
Lasocki, Karol and
Yu, Yi and
Takasu, Atsuhiro",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2024",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-eacl.89/",
pages = "1336--1346",
abstract = "The generation of lyrics tightly connected to accompanying melodies involves establishing a mapping between musical notes and syllables of lyrics. This process requires a deep understanding of music constraints and semantic patterns at syllable-level, word-level, and sentence-level semantic meanings. However, pre-trained language models specifically designed at the syllable level are publicly unavailable. To solve these challenging issues, we propose to exploit fine-tuning character-level language models for syllable-level lyrics generation from symbolic melody. In particular, our method aims to fine-tune a character-level pre-trained language model, allowing to incorporation of linguistic knowledge of the language model into the beam search process of a syllable-level Transformer generator network. Besides, by exploring ChatGPT-based evaluation of generated lyrics in addition to human subjective evaluation, we prove that our approach improves the coherence and correctness of generated lyrics, without the need to train expensive new language models."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-syllable">
<titleInfo>
<title>Syllable-level lyrics generation from melody exploiting character-level language model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhe</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karol</namePart>
<namePart type="family">Lasocki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atsuhiro</namePart>
<namePart type="family">Takasu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The generation of lyrics tightly connected to accompanying melodies involves establishing a mapping between musical notes and syllables of lyrics. This process requires a deep understanding of music constraints and semantic patterns at syllable-level, word-level, and sentence-level semantic meanings. However, pre-trained language models specifically designed at the syllable level are publicly unavailable. To solve these challenging issues, we propose to exploit fine-tuning character-level language models for syllable-level lyrics generation from symbolic melody. In particular, our method aims to fine-tune a character-level pre-trained language model, allowing to incorporation of linguistic knowledge of the language model into the beam search process of a syllable-level Transformer generator network. Besides, by exploring ChatGPT-based evaluation of generated lyrics in addition to human subjective evaluation, we prove that our approach improves the coherence and correctness of generated lyrics, without the need to train expensive new language models.</abstract>
<identifier type="citekey">zhang-etal-2024-syllable</identifier>
<location>
<url>https://aclanthology.org/2024.findings-eacl.89/</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>1336</start>
<end>1346</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Syllable-level lyrics generation from melody exploiting character-level language model
%A Zhang, Zhe
%A Lasocki, Karol
%A Yu, Yi
%A Takasu, Atsuhiro
%Y Graham, Yvette
%Y Purver, Matthew
%S Findings of the Association for Computational Linguistics: EACL 2024
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F zhang-etal-2024-syllable
%X The generation of lyrics tightly connected to accompanying melodies involves establishing a mapping between musical notes and syllables of lyrics. This process requires a deep understanding of music constraints and semantic patterns at syllable-level, word-level, and sentence-level semantic meanings. However, pre-trained language models specifically designed at the syllable level are publicly unavailable. To solve these challenging issues, we propose to exploit fine-tuning character-level language models for syllable-level lyrics generation from symbolic melody. In particular, our method aims to fine-tune a character-level pre-trained language model, allowing to incorporation of linguistic knowledge of the language model into the beam search process of a syllable-level Transformer generator network. Besides, by exploring ChatGPT-based evaluation of generated lyrics in addition to human subjective evaluation, we prove that our approach improves the coherence and correctness of generated lyrics, without the need to train expensive new language models.
%U https://aclanthology.org/2024.findings-eacl.89/
%P 1336-1346
Markdown (Informal)
[Syllable-level lyrics generation from melody exploiting character-level language model](https://aclanthology.org/2024.findings-eacl.89/) (Zhang et al., Findings 2024)
ACL