Open AccessWatsonPaths: Scenario‐Based Question Answering and Inference over Unstructured Information
Author(s) -
Lally Adam,
Bagchi Sugato,
Barborak Michael A.,
Buchanan David W.,
ChuCarroll Jennifer,
Ferrucci David A.,
Glass Michael R.,
Kalyanpur Aditya,
Mueller Erik T.,
Murdock J. William,
Patwardhan Siddharth,
Prager John M.
Publication year - 2017
Publication title -
ai magazine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.597
H-Index - 79
eISSN - 2371-9621
pISSN - 0738-4602
DOI - 10.1609/aimag.v38i2.2715
Subject(s) - watson , inference , computer science , question answering , probabilistic logic , set (abstract data type) , information retrieval , graph , ask price , ibm , artificial intelligence , data science , theoretical computer science , programming language , materials science , economy , economics , nanotechnology
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. Watson‐Paths 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 graphic 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.