Creative Help: A Story Writing Assistant (bibtex)
by Roemmele, Melissa and Gordon, Andrew S.
Abstract:
We present Creative Help, an application that helps writers by generating suggestions for the next sentence in a story as it being written. Users can modify or delete suggestions according to their own vision of the unfolding narrative. The application tracks users' changes to suggestions in order to measure their perceived helpfulness to the story, with fewer edits indicating more helpful suggestions. We demonstrate how the edit distance between a suggestion and its resulting modi⬚cation can be used to comparatively evaluate di⬚erent models for generating suggestions. We describe a generation model that uses case-based reasoning to find relevant suggestions from a large corpus of stories. The application shows that this model generates suggestions that are more helpful than randomly selected suggestions at a level of marginal statistical signifcance. By giving users control over the generated content, Creative Help provides a new opportunity in open-domain interactive storytelling.
Reference:
Creative Help: A Story Writing Assistant (Roemmele, Melissa and Gordon, Andrew S.), Chapter in Interactive Storytelling, Springer International Publishing, volume 9445, 2015.
Bibtex Entry:
@incollection{roemmele_creative_2015,
	address = {Copenhagen, Denmark},
	title = {Creative {Help}: {A} {Story} {Writing} {Assistant}},
	volume = {9445},
	isbn = {978-3-319-27036-4},
	url = {http://link.springer.com/10.1007/978-3-319-27036-4_8},
	abstract = {We present Creative Help, an application that helps writers by generating suggestions for the next sentence in a story as it being written. Users can modify or delete suggestions according to their own vision of the unfolding narrative. The application tracks users' changes to suggestions in order to measure their perceived helpfulness to the story, with fewer edits indicating more helpful suggestions. We demonstrate how the edit distance between a suggestion and its resulting modi⬚cation can be used to comparatively evaluate di⬚erent models for generating suggestions. We describe a generation model that uses case-based reasoning to find relevant suggestions from a large corpus of stories. The application shows that this model generates suggestions that are more helpful than randomly selected suggestions at a level of marginal statistical signifcance. By giving users control over the generated content, Creative Help provides a new opportunity in open-domain interactive storytelling.},
	booktitle = {Interactive {Storytelling}},
	publisher = {Springer International Publishing},
	author = {Roemmele, Melissa and Gordon, Andrew S.},
	month = dec,
	year = {2015},
	keywords = {The Narrative Group},
	pages = {81--92}
}
Powered by bibtexbrowser