WatsonPaths: Scenario-Based Question Answering and Inference over Unstructured Information

Authors

  • Adam Lally Information Technology and Services
  • Sugato Bagchi IBM Research
  • Michael A. Barborak IBM T. J. Watson Research Center
  • David W. Buchanan IBM T. J. Watson Research Center
  • Jennifer Chu-Carroll IBM Research
  • David A. Ferrucci Bridgewater
  • Michael R. Glass IBM Research
  • Aditya Kalyanpur IBM T. J. Watson Research Center
  • Erik T. Mueller Capital One
  • J. William Murdock IBM T. J. Watson Research Center
  • Siddharth Patwardhan IBM T. J. Watson Research Center
  • John M. Prager IBM T. J. Watson Research Center

DOI:

https://doi.org/10.1609/aimag.v38i2.2715

Abstract

We present WatsonPaths, a novel system that can answer scenario-based questions. These include medical questions that present a patient summary and ask for the most likely diagnosis or most appropriate treatment. WatsonPaths builds on the IBM Watson question answering system. WatsonPaths breaks down the input scenario into individual pieces of information, asks relevant subquestions of Watson to conclude new information, and represents these results in a graphical model. Probabilistic inference is performed over the graph to conclude the answer. On a set of medical test preparation questions, WatsonPaths shows a significant improvement in accuracy over multiple baselines.

Downloads

Published

2017-07-01

How to Cite

Lally, A., Bagchi, S., Barborak, M. A., Buchanan, D. W., Chu-Carroll, J., Ferrucci, D. A., Glass, M. R., Kalyanpur, A., Mueller, E. T., Murdock, J. W., Patwardhan, S., & Prager, J. M. (2017). WatsonPaths: Scenario-Based Question Answering and Inference over Unstructured Information. AI Magazine, 38(2), 59-76. https://doi.org/10.1609/aimag.v38i2.2715

Issue

Section

Articles