Weird AI Yankovic: Generating Parody Lyrics
This addresses the problem of controllable text generation for lyric parody creation, which is incremental as it builds on existing methods like XLNet.
The paper tackled the challenge of generating parody lyrics that meet syllable and rhyme constraints by introducing the Weird AI Yankovic system, which uses specialized sampling and backward text generation with XLNet to reliably produce such lyrics.
Lyrics parody swaps one set of words that accompany a melody with a new set of words, preserving the number of syllables per line and the rhyme scheme. Lyrics parody generation is a challenge for controllable text generation. We show how a specialized sampling procedure, combined with backward text generation with XLNet can produce parody lyrics that reliably meet the syllable and rhyme scheme constraints.We introduce the Weird AI Yankovic system and provide a case study evaluation. We conclude with societal implications of neural lyric parody generation.