Component-based approach to automatic poetry generation

Анна Владимировна Мосолова, Иван Бондаренко, Петр Андреевич Гусев, Анастасия Дмитриевна Малышева, Даниил Иванович Водолазский, Мария Николаевна Боровикова

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review


This paper describes two approaches to generating poetic texts on a given topic, one of which we used while participating in ClassicAI, a contest in developing poetry generators in a specific style held by Sberbank. In the first one, we used topic modeling for extracting keywords that a certain topic is characteristic of, applied a text data augmenter to replace parts of the source of the poetry style with thematic words, and then applied a poetic consistency checker to maintain rhyme and rhythm in the output text. In the second one, we used semantic search for obtaining odd lines for the output texts and then phonetic search that selected lines similar in rhyme and rhythm to the given lines and used them as even ones. In this paper, we describe both of our approaches, analyze their benefits and weak spots, provide information on the results of the competition and suggest possible improvements
Translated title of the contributionКомпонентный подход к автоматической генерации текстов
Original languageEnglish
Title of host publicationComputational Linguistics and Intellectual Technologies
Subtitle of host publicationPapers from the Annual International Conference “Dialogue” (2019)
EditorsВладимир Павлович Селегей
Place of PublicationМосква
Publication statusPublished - 2019



Fingerprint Dive into the research topics of 'Component-based approach to automatic poetry generation'. Together they form a unique fingerprint.

Cite this