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

Abstract

We present WatsonPaths TM , a novel system that can answer scenario-based questions, for example medical questions that present a patient summary and ask for the most likely diagnosis or most appropriate treatment. WatsonPaths builds on the IBM Watson TM question answering system that takes natural language questions as input and produces precise answers along with accurate confidences as output. 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 the base Watson QA system. We also describe how WatsonPaths can be used in a collaborative application to help users reason about complex scenarios.

7 Figures and Tables

020406020162017
Citations per Year

Citation Velocity: 14

Averaging 14 citations per year over the last 2 years.

Learn more about how we calculate this metric in our FAQ.

Cite this paper

@article{Lally2017WatsonPathsSQ, title={WatsonPaths: Scenario-Based Question Answering and Inference over Unstructured Information}, author={Adam Lally and Sugato Bagchi and Michael Barborak and David W. Buchanan and Jennifer Chu-Carroll and David A. Ferrucci and Michael R. Glass and Aditya Kalyanpur and Erik T. Mueller and J. William Murdock and Siddharth Patwardhan and John M. Prager}, journal={AI Magazine}, year={2017}, volume={38}, pages={59-76} }