Abstract
Through advances in neural language modeling, it has become possible to generate artificial texts in a variety of genres and styles. While the semantic coherence of such texts should not be over-estimated, the grammatical correctness and stylistic qualities of these artificial texts are at times remarkably convincing. In this paper, we report a study into crowd-sourced authenticity judgments for such artificially generated texts. As a case study, we have turned to rap lyrics, an established sub-genre of present-day popular music, known for its explicit content and unique rhythmical delivery of lyrics. The empirical basis of our study is an experiment carried out in the context of a large, mainstream contemporary music festival in the Netherlands. Apart from more generic factors, we model a diverse set of linguistic characteristics of the input that might have functioned as authenticity cues. It is shown that participants are only marginally capable of distinguishing between authentic and generated materials. By scrutinizing the linguistic features that influence the participants’ authenticity judgments, it is shown that linguistic properties such as ‘syntactic complexity’, ‘lexical diversity’ and ‘rhyme density’ add to the user’s perception of texts being authentic. This research contributes to the improvement of the quality and credibility of generated text. Additionally, it enhances our understanding of the perception of authentic and artificial art.
Highlights
Due to recent advances in computer technology, communication—be it verbal or not—is no longer a privileged kind of interaction that can only take place between human agents
We condition our models on sentence length and final sentence phonology. This conditioning allows us to enhance the realism of the generated rap lyrics by biasing the generative process towards particular verse structures and higher rhyme density
We model the effect of trial number as a monotonic effect, which allows us to efficiently estimate predictors on an ordinal scale [39]
Summary
Due to recent advances in computer technology, communication—be it verbal or not—is no longer a privileged kind of interaction that can only take place between human agents. People interact with a variety of artificial agents, sometimes even without being fully aware of whether or not their conversation partners are human. Chatbot interfaces for customers at company websites are but one example of a popular application of this technology that is rapidly gaining popularity [1]. Natural Language Generation is increasingly high on the international research agenda [2]. Through advances in neural language modeling, it has become possible to generate synthetic texts in a variety of genres.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
