Abstract
While developing a story, novices and published writers alike have had to look outside themselves for inspiration. Language models have recently been able to generate text fluently, producing new stochastic narratives upon request. However, effectively integrating such capabilities with human cognitive faculties and creative processes remains challenging. We propose to investigate this integration with a multimodal writing support interface that offers writing suggestions textually, visually, and aurally. We conduct an extensive study that combines elicitation of prior expectations before writing, observation and semi-structured interviews during writing, and outcome evaluations after writing. Our results illustrate the individual and situational variation in machine-in-the-loop writing approaches, suggestion acceptance, and ways the system is helpful. Centrally, we report how participants performintegrative leaps, by which they do cognitive work to integrate suggestions of varying semantic relevance into their developing stories. We interpret these findings, offering modeling and design recommendations for future creative writing support technologies.
Highlights
Augmented writing systems pervade human-computer interaction in everyday life, taking various forms to suit speciic tasks
If we’re talking about machine learning systems, they are trained with large corpi of data that are curated by data scientists or machine learning engineers
7 CONCLUSION This research presents an extensive study of machine-in-the-loop creative writing, centered around a new interface that makes writing suggestions through sight, sound, and language
Summary
Augmented writing systems pervade human-computer interaction in everyday life, taking various forms to suit speciic tasks. Recent work in machine learning, intended to improve performance on these tasks and others (such as machine translation and text summarization), has given rise to formidable natural language understanding and generation models [16, 81] These are often demonstrated by application to automated or semi-automated narrative generation tasks [1, 62, 76], an essentially creative domain. Much remains unexplored about how emerging methods in AI, machine learning, and natural language processing might inluence creative writing, in part due to the ambiguity and variability of human writing processes These processes go beyond the linear projection from idea to a full text; research shows how planning narratives, translating ideas into visible textual material, and reviewing are all happening and interacting throughout the process rather than simple sequential stages [36, 67]. This is a very familiar process for humans when communicating through writing; as every writer knows, having good ideas does not automatically
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
