Eric Yeh

Current Projects

Task Assistant Task Assistant is a flexible, web-based workflow application that enables an organization to move its operating procedures from manuals and human memories into living collaborative artifacts. Task Assistant is fully collaborative, allowing multiple users to simultaneous edit, build, or execute workflows.

Past Projects

	HARP: Human Augmented Reasoning through Patterning This project developed: 1) cognitive aids that allow humans and machines to "think together" in real-time about complicated problems; 2) techniques to overcome the biases and limitations of the human cognitive system; 3) "cognitive amplifiers" that help teams of people rapidly and fully comprehend complicated and uncertain situations; and, 4) the means to rapidly and seamlessly cut across and complement existing hierarchical organizational structures.
	PRIME: A Predictive Model Development Environment The goal was to develop PRIME, an effects-based modelling tool, as a web application. PRIME supports rapid, collaborative development of forecasts of the effects of a planned set of DIME (diplomatic, informational, military, or economic) actions.
	TransPAL: Transitioning PAL Technologies The TransPAL project is transitioning a number of technologies developed on the DARPA PAL program for use by various members of the Armed Services.

Software

	Angler Angler is a tool that helps intelligence/policy professionals explore, understand, and overcome cognitive biases, and collaboratively expand their joint cognitive vision through use of divergent & convergent thinking techniques (such as brainstorming and clustering).
	LAW: Link Analysis Workbench LAW is a system that helps intelligence professionals define and match patterns within large, incomplete, and noisy sets of relational data.
	PRIME The Probative Rapid Interactive Modeling Environment (PRIME) is a decision-support web application that provides modeling and reasoning capabilities intended to stretch the thinking of analysts and decision makers by producing a forecast of the plausible effects that could result from taking actions in a given situation. The plausibility of each forecast effect is explained by one or more structured arguments.
	SEAS: Structured Evidential Argumentation System SEAS is a tool to aid analysts in reasoning about potential opportunities/crises. It records analytic thinking in structured arguments, provides a collaborative environment in which multiple analysts can simultaneously contribute to arguments, and retains a coproate memory of the evolution of analytic thinking over time.

Publications

The following are in reverse chronological order of publication.
Showing most recent 5 out of 12 [View All]

• Yeh, E. and Jarrold, W. and Jordan, J. Leveraging Psycholinguistic Resources and Emotional Sequence models for Suicide Note Emotion Annotation. Biomedical Informatics Insights, vol. 5, pp. 155-163, 2012.  [PDF, Details]

• Gervasio, M. and Yeh, E. and Myers, K. Learning to Ask the Right Questions to Help a Learner Learn, in Proceedings of the 2011 International Conference on Intelligent User Interfaces, 2011.  [Details]

• Gervasio, M. and Yeh, E. and Myers, K. Learning to Ask the Right Questions, in Proceedings of the AAMAS Workshop on Agents Learning Interactively from Human Teachers , 2010.  [PDF, Details]

• Yeh, E. Graph Extraction and Edit Strategies for Textual Entailment, Masters Thesis. Stanford University, 2010.  [Details]

• Jarrold, W.L. and Peintner, B. and Yeh, E. and Krasnow, R. and Javitz, H.S. and Swan, G.E. Language Analytics for Assessing Brain Health: Cognitive Impairment, Depression and Pre-Symptomatic Alzheimer’s Disease, in Brain Informatics, Proceedings BI 2010, Lecture Notes in Artificial Intelligence, Springer-Verlag, vol. 6334, pp. 299-307, 2010.  [Details]