Evaluating Creative Language Generation: The Case of Rap Lyric Ghostwriting
This work addresses the challenge of quantifying creativity and style in language generation for researchers in computational creativity and natural language processing, though it is incremental in focusing on a specific domain.
The paper tackled the problem of evaluating creative language generation, specifically rap lyric ghostwriting, by developing a novel evaluation methodology that assesses stylistic similarity and content distinctiveness, and provided a corpus of lyrics for 13 rap artists annotated for style.
Language generation tasks that seek to mimic human ability to use language creatively are difficult to evaluate, since one must consider creativity, style, and other non-trivial aspects of the generated text. The goal of this paper is to develop evaluation methods for one such task, ghostwriting of rap lyrics, and to provide an explicit, quantifiable foundation for the goals and future directions of this task. Ghostwriting must produce text that is similar in style to the emulated artist, yet distinct in content. We develop a novel evaluation methodology that addresses several complementary aspects of this task, and illustrate how such evaluation can be used to meaningfully analyze system performance. We provide a corpus of lyrics for 13 rap artists, annotated for stylistic similarity, which allows us to assess the feasibility of manual evaluation for generated verse.