Watson: Beyond Jeopardy!

In 2007, IBM Research took on the grand challenge of building a computer system that can perform well enough on open-domain question answering to compete with champions at the game of Jeopardy! In 2011, the open-domain question answering system dubbed Watson beat the two highest ranked players in a two-game Jeopardy! match. But, to what degree can the QA technology underlying Watson, called DeepQA, which was tuned for answering Jeopardy! questions, succeed in a dramatically different and extremely specialized domain such as medicine? This paper describes the steps needed to adapt and improve performance in this as well as other domains. In addition, whereas Jeopardy! allows only "question in, single answer out" with no explanation, we elaborate upon a vision for an evidence-based clinical decision support system, based on the DeepQA technology, that affords exploration of a broad range of hypotheses and their associated evidence, as well as uncovers missing information that can be used in mixed-initiative dialog.

By: David Ferrucci, Anthony Levas, Sugato Bagchi, David Gondek, Erik Mueller

Published in: Artificial Intelligence, volume 199-200, (no ), pages 93-105 in 2013

Please obtain a copy of this paper from your local library. IBM cannot distribute this paper externally.

Questions about this service can be mailed to reports@us.ibm.com .