Generating lyrics using constrained random walks on a word network

Babnik, Žiga (author), Pegan, Jasmina (author), Kos, Domen (author), Šubelj, Lovro (author)

In the paper we present an approach for automatic lyrics generation. From the American National Corpusof written texts we build a Word Network, which encodes word sequences. Lyrics are then generated by performing a constrained random walk over the Word Network. The constraints include the structure of the generated sentence, the rhythm of the lines of the stanza or the rhymes of the stanza itself. Lyrics are generated using each constraint individually and also using all three constraints at the same time. We tested the single constraint strategies using a toy example, while the results of the joint strategy were subject to human review. While the given properties of the toy example, were kept in the results, replicating the toy example perfectly proved a difficult task. The results of the questionnaire showed that lack of a deeper meaning and strange capitalization were the main reasons that our results did not appear as though they were written by a human.

• Language: English
• Keywords: poetry generation, Markov models, network analysis, semantics
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FRI - Faculty of Computer and Information Science
• Publication status: Published
• Publication version: Version of Record
• Year: 2024
• Number of pages: Str. 131-140
• Numbering: Vol. 48, no. 1
• PID: 20.500.12556/RUL-155137
• UDC: 004
• ISSN on article: 0350-5596
• COBISS.SI-ID: 189731587
• Publication date in RUL: 21.03.2024

Record is a part of a journal

• Title: Informatica : an international journal of computing and informatics
• Shortened title: Informatica
• Publisher: Slovene Society Informatika
• ISSN: 0350-5596
• COBISS.SI-ID: 746244

Licences

• License: CC BY 3.0, Creative Commons Attribution 3.0 Unported
• Link: https://creativecommons.org/licenses/by/3.0/deed.en
• Description: You are free to reproduce and redistribute the material in any medium or format. You are free to remix, transform, and build upon the material for any purpose, even commercially. You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use. You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.

Secondary language

• Language: Slovenian

Abstract

Avtomatsko generiranje besedil pesmi bazira na uporabi omejenih naključnih sprehodov po besednem omrežju Word Network, vzpostavljenem iz Ameriškega nacionalnega korpusa. Besedila se generirajo z upoštevanjem strukture stavka, ritma in rim.

• Keywords: generiranje poezije, Markovski modeli, analiza omrežij, semantika