Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Posts
Future Blog Post
Published:
This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.
Blog Post number 4
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 3
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 2
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 1
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
portfolio
Portfolio item number 1
Short description of portfolio item number 1
Portfolio item number 2
Short description of portfolio item number 2
publications
LISA: Lexically Intelligent Story Assistant
Published in 13th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2017, 2017
LISA (Lexically Intelligent Story Assistant) is an AI-powered assistive tool designed to help story writers improve their narratives through intelligent analysis and feedback. The system analyzes natural language stories to build comprehensive knowledge bases, then uses artificial intelligence to detect and highlight lexical inconsistencies, plot holes, and narrative errors in real-time. LISA goes beyond simple spell-checking by understanding story context and character relationships, allowing writers to query the system in natural language about their story elements. This work demonstrates how AI can be leveraged to create databases from narrative content and provide meaningful assistance to creative writers, representing an important step toward computational creativity tools for storytelling.
Recommended citation: Sanghrajka, R., Hidalgo, D., Chen, P., & Kapadia, M. (2017). LISA: Lexically Intelligent Story Assistant. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 13(1), 221-227. https://doi.org/10.1609/aiide.v13i1.12956
Download Paper
Computer-assisted Authoring for Natural Language Story Scripts
Published in 30th Conference on Innovative Applications of Artificial Intelligence, IAAI-18, 2018
This work presents an advanced computer-assisted authoring system designed to help scriptwriters during the story-writing process through intelligent natural language analysis. The system extracts comprehensive information from natural language stories and enables both story-centric and character-centric reasoning capabilities. A key innovation is the introduction of “knowledge bytes” as atomic units of information that allow the system to parse narrative text into structured, queryable data. The system provides intuitive querying interfaces that enable scriptwriters to ask natural language questions about story and character information, leveraging logical reasoning to provide intelligent responses. This research demonstrates how AI can transform the creative writing process by making narrative information more accessible and analyzable for authors.
Recommended citation: Sanghrajka, R., Witoń, W., Schriber, S., Gross, M., & Kapadia, M. (2018). Computer-Assisted Authoring for Natural Language Story Scripts. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). https://doi.org/10.1609/aaai.v32i1.11420
Download Paper
CARDINAL: Computer-assisted Authoring of Movie Scripts
Published in 23rd International Conference on Intelligent User Interfaces, IUI 2018, 2018
CARDINAL is a computer-assisted authoring tool designed to help scriptwriters create and edit movie scripts through intelligent automated analysis of natural language scripts. The system provides multiple perspectives for viewing and interpreting scripts by generating different intermediate representations from the narrative text. CARDINAL creates both 2D and 3D visualizations of scripted narratives and presents character interactions in an intuitive timeline-based view, empowering scriptwriters to understand their stories from spatial and temporal perspectives. This work represents a significant advancement in computational creativity tools, bridging natural language processing with visual storytelling.
Recommended citation: Marti, M., Vieli, J., Witoń, W., Sanghrajka, R., Inversini, D., Wotruba, D., Simo, I., Schriber, S., Gross, M., & Kapadia, M. (2018). CARDINAL: Computer Assisted Authoring of Movie Scripts. In Proceedings of the 23rd International Conference on Intelligent User Interfaces (IUI '18). ACM, New York, NY, USA. https://doi.org/10.1145/3172944.3172972
Download Paper
Leveraging Cognitive Models in Planning to Assist Narrative Authoring
Published in 14th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2018., 2018
This was my doctoral consortium abstract presented at the beginning of my PhD, outlining my research vision for integrating cognitive models into narrative planning systems. The work explores how cognitive models can determine how actions and events in narratives affect audiences, with the goal of leveraging these models in narrative planning to provide intelligent narrative plans. The research aimed to create collaborative systems where human authors could work with computational systems on narrative generation, bridging cognitive science with computational storytelling.
Recommended citation: Sanghrajka, R. (2018). Leveraging Cognitive Models in Planning to Assist Narrative Authoring. Proceedings of the Fourteenth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE 2018), 293.
Download Paper
A Knowledge Representation for Planning-Based Story Generation Applied to the Manual and Automatic Encoding of Plot
Published in 12th International Conference on Interactive Digital Storytelling ICIDS 2019, 2019
This work introduces HeadCode, a novel coding scheme for story structure that maps directly to formal models of story generation, specifically focusing on character beliefs and the complexities that arise when mistaken beliefs lead to action failure. The research addresses a significant gap in existing story coding schemes by providing a framework that can handle failed actions and character misconceptions in narrative planning systems. This was part of my PhD work with Michael Young at University of Utah, developing more sophisticated representations for computational storytelling that could capture the nuanced psychology of character behavior in narratives.
Recommended citation: Sanghrajka, R., & Young, R. M. (2019). A Knowledge Representation for Planning-Based Story Generation Applied to the Manual and Automatic Encoding of Plot. In R. Cardona-Rivera, A. Sullivan, & R. Young (Eds.), Interactive Storytelling. ICIDS 2019. Lecture Notes in Computer Science, vol 11869 (pp. 318-322). Springer. https://doi.org/10.1007/978-3-030-33894-7_31
Download Paper
SHOWRUNNER: A Tool for Storyline Execution/Visualization in 3D Game Environments
Published in 12th International Conference on Interactive Digital Storytelling, ICIDS 2019, 2019
ShowRunner is a tool for visualizing story world execution within 3D game environments, taking abstract declarative story scripts and mapping them to game engine data elements to execute narrative actions. The system uses virtual cameras to film and present the story action to users, bridging the gap between high-level narrative planning and low-level game engine visualization. This work was developed during my time at University of Utah with my adviser R. Michael Young, focusing on creating practical tools that could bring computational narratives to life in interactive 3D environments.
Recommended citation: Sanghrajka, R., Young, R. M., Salisbury, B., & Lang, E. W. (2019). ShowRunner: A Tool for Storyline Execution/Visualization in 3D Game Environments. In R. Cardona-Rivera, A. Sullivan, & R. Young (Eds.), Interactive Storytelling. ICIDS 2019. Lecture Notes in Computer Science, vol 11869 (pp. 323-327). Springer. https://doi.org/10.1007/978-3-030-33894-7_32
Download Paper
OpenTutor: Designing a Rapid-Authored Tutor That Learns As You Grade.
Published in The International Florida Artificial Intelligence Research Society (FLAIRS) Conference, 2021
This paper is work that I did while interning at the Institute of Creative Technologies (ICT) at the University of Southern California (USC). It focuses on building an adaptive AI tutor.
Recommended citation: Nye, B. D., Sanghrajka, R., Bodhwani, V., Acob, M., Budziwojski, D., Carr, K., Kirshner, L. & Swartout, W. R. (2021, April). OpenTutor: Designing a Rapid-Authored Tutor that Learns as you Grade. In The International FLAIRS Conference Proceedings (Vol. 34).
Download Paper
Generating QUEST Representations for Narrative Plans Consisting of Failed Actions
Published in UX of AI Workshop at International Conference on the Foundations of Digital Games, FDG 2021, 2021
This work extends narrative planning algorithms to generate QUEST representations for story plans that include failed character actions, building on our HeadSpace system for modeling character beliefs and action failures. The paper presents computational methods for translating complex narrative plans containing failed actions into structured representations that can be used for game design and interactive storytelling.
Recommended citation: Sanghrajka, R., Lang, E. W., & Young, R. M. (2021). Generating QUEST Representations for Narrative Plans Consisting of Failed Actions. UX of AI Workshop held at the International Conference on the Foundations of Digital Games (FDG'21).
Download Paper
HeadSpace: Incorporating Action Failure and Character Beliefs into Narrative Planning
Published in AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE'22), 2022
This paper is the conference version of HeadSpace, a FF-style heuristic search state-space narrative planner that can construct plans where characters can attempt (and fail) actions which they believe are executable in the world due to incorrect beliefs about the preconditions of the action.
Recommended citation: Sanghrajka, R., Young, R. M., & Thorne, B. (2022, October). Headspace: incorporating action failure and character beliefs into narrative planning. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (Vol. 18, No. 1, pp. 171-178).
Download Paper
A Case-Based Reasoning Approach to Plugin Parameter Selection in Vocal Audio Production
Published in Case-Based Reasoning Research and Development: 30th International Conference, ICCBR 2022., 2022
This is work that was spearheaded by Michael Clemens, who works in computational creativity for audio. In this paper, we used case-based reasoning to automatically use default parameters for vocal audio production.
Recommended citation: Clemens, M., Blackburn, N. N., Sanghrajka, R., Ali, M., Gardone, M., Thomas, S., Finney, H. & Cardona-Rivera, R. E. (2022, August). A Case-Based Reasoning Approach to Plugin Parameter Selection in Vocal Audio Production. In International Conference on Case-Based Reasoning (pp. 350-364). Cham: Springer International Publishing.
Download Paper
Evaluating Reader Comprehension of Plan-Based Stories Containing Failed Actions
Published in 18th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2022, 2022
This work presents a comprehension-based evaluation approach for computationally constructed stories containing failed actions, focusing on how readers understand plot lines generated by our HeadSpace system. We conducted empirical studies to measure reader comprehension of narratives where characters’ actions fail due to mistaken beliefs, moving beyond purely analytical evaluations of story generation systems. This was a key part of my PhD dissertation research, providing crucial validation that our sophisticated narrative planning algorithms actually produce stories that human readers can understand and engage with meaningfully.
Recommended citation: Sanghrajka, R., & Young, R. M. (2022). Evaluating Reader Comprehension of Plan-Based Stories Containing Failed Actions. Proceedings of the Eighteenth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE 2022). AAAI Press.
Download Paper
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
FIGS: Exploring Computer Science
Undergraduate Course, Rutgers University, School of Arts and Sciences, 2016
This was a one-credit First-year Interest Group Seminar (FIGS) that I designed and taught to 30 first-year students over 10 weeks. The course served as both an introduction to computer science concepts and a college transition program, combining academic exploration with mentorship and community building.