Institute for Creative Technologies

Download a one sheet PDF overview of this project.

The Story Representation and Management project at ICT is aimed at developing technologies for the collection, analysis and use of millions of personal stories in support of artificial intelligence and knowledge management applications.

Research focuses on:

• Story-Based Knowledge Management -- Technologies for capturing narratives of real world experiences in collections of written text (e.g. Internet weblogs) and retrieving them based on their semantic content
• Story-Based Reasoning and Simulation -- Technologies for using large-scale story collections as a knowledge base to support automated reasoning about events

Applications include:
Story Upgrade: A Story-Based Knowledge-Management Application
The phenomenal rise of Internet weblogging has created new opportunities for people to tell personal stories of their life experience, and the potential to share these stories with those who can most benefit from reading them. One barrier to this new mode of storytelling is the lack of accessibility; existing Internet search tools are not tailored to the unique characteristics of this textual genre. This application is a search engine specifically for the stories that appear in Internet weblogs. It utilizes statistical text classification technologies to separate story content from other text in weblog entries, and facilitates searches for stories that are related to particular activities of interest.

Say Anything: Massively Collaborative Interactive Storytelling
Say Anything is a text-based interactive storytelling application, where a user and the computer collaboratively author a story by taking turns contributing new sentences. The user's contributions are limited only by their creativity. The computer's contributions are selected from tens of millions of sentences extracted from personal stories that people write in their weblogs. The Say Anything application demonstrates a solution to the content-authoring problem in interactive storytelling research.

This project differs from others in the following ways:

• Specific focus on the discourse genre of nonfiction narratives of people's experiences
• Commitment to the integration of large-scale knowledge repositories in the interpretation of textual data
• Focus on natural language descriptions of narrative events instead of hand-authored formal representations

Tags: automated, experience, interpretation, narrative, story

View All Projects »