Annotating High-Level Structures of Short Stories and Personal Anecdotes
This work addresses the challenge of operationalizing narrative theories for AI systems to improve human-computer communication, but it is incremental as it builds on existing theories without introducing new computational methods.
The researchers tackled the limited computational understanding of high-level narrative structures by developing an annotation scheme based on narratological theories and annotating 360 short stories from online sources.
Stories are a vital form of communication in human culture; they are employed daily to persuade, to elicit sympathy, or to convey a message. Computational understanding of human narratives, especially high-level narrative structures, remain limited to date. Multiple literary theories for narrative structures exist, but operationalization of the theories has remained a challenge. We developed an annotation scheme by consolidating and extending existing narratological theories, including Labov and Waletsky's (1967) functional categorization scheme and Freytag's (1863) pyramid of dramatic tension, and present 360 annotated short stories collected from online sources. In the future, this research will support an approach that enables systems to intelligently sustain complex communications with humans.