Building Watson: An Overview of the DeepQA Project

TLDR

The challenge involved deploying a real‑time automatic contestant on Jeopardy, rather than a laboratory exercise. IBM Research aimed to build a real‑time computer system capable of competing at the human champion level on Jeopardy, using the challenge to drive the design of the DeepQA architecture and Watson. The DeepQA architecture was designed and Watson implemented to meet the real‑time Jeopardy requirements. Watson achieved human‑expert performance on Jeopardy in precision, confidence, and speed, and DeepQA proved to be an effective, extensible architecture for advancing QA research.

Abstract

IBM Research undertook a challenge to build a computer system that could compete at the human champion level in real time on the American TV quiz show, Jeopardy. The extent of the challenge includes fielding a real‐time automatic contestant on the show, not merely a laboratory exercise. The Jeopardy Challenge helped us address requirements that led to the design of the DeepQA architecture and the implementation of Watson. After three years of intense research and development by a core team of about 20 researchers, Watson is performing at human expert levels in terms of precision, confidence, and speed at the Jeopardy quiz show. Our results strongly suggest that DeepQA is an effective and extensible architecture that can be used as a foundation for combining, deploying, evaluating, and advancing a wide range of algorithmic techniques to rapidly advance the field of question answering (QA).