Building Watson: An Overview of the DeepQA Project

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 3 years of intense research and development by a core team of about 20 researches, 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 may be used as a foundation for combining, deploying, evaluating and advancing a wide range of algorithmic techniques to rapidly advance the field of QA.

[1]  Bill Broyles.  Notes , 1907, The Classical Review.

[2]  J. Stockwell.  Towards the open: By Henry C. Tracy with an Introduction by Julian Huxley. xx-257 pages, 6 × in., cloth. New York, E. P. Dutton & Co., 1927. Price, $3.50 , 1928 .

[3]  Warren Bower.  New directions , 1937 .

[4]  Robert F. Simmons,et al.  Computational Linguistics Natural Language Question- Answering Systems: 1969 , 2022 .

[5]  M S Waterman,et al.  Identification of common molecular subsequences. , 1981, Journal of molecular biology.

[6]  Michael J. Pazzani,et al.  Knowledge Based Question Answering , 1983, ANLP.

[7]  Michael C. McCord,et al.  Slot Grammar: A System for Simpler Construction of Practical Natural Language Grammars , 1989, Natural Language and Logic.

[8]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[9]  G. Miller.  WordNet: A Lexical Database for English , 1992, HLT.

[10]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[11]  David H. Wolpert,et al.  Stacked generalization , 1992, Neural Networks.

[12]  Douglas B. Lenat,et al.  CYC: a large-scale investment in knowledge infrastructure , 1995, CACM.

[13]  Thore Graepel,et al.  Large Margin Rank Boundaries for Ordinal Regression , 2000 .

[14]  Ellen M. Voorhees,et al.  Overview of the TREC 2002 Question Answering Track , 2003, TREC.

[15]  Eduard Hovy,et al.  Knowledge-Based Question Answering , 2002 .

[16]  Feng-Hsiung Hsu,et al.  Behind Deep Blue: Building the Computer that Defeated the World Chess Champion , 2002 .

[17]  Thorsten Joachims,et al.  Optimizing search engines using clickthrough data , 2002, KDD.

[18]  Sanda M. Harabagiu,et al.  COGEX: A Logic Prover for Question Answering , 2003, NAACL.

[19]  Andrew McCallum,et al.  Dynamic conditional random fields: factorized probabilistic models for labeling and segmenting sequence data , 2004, J. Mach. Learn. Res..

[20]  Mark T. Maybury.  New Directions in Question Answering , 2004 .

[21]  David A. Ferrucci,et al.  UIMA: an architectural approach to unstructured information processing in the corporate research environment , 2004, Natural Language Engineering.

[22]  Kenneth D. Forbus,et al.  Analysis of Strategic Knowledge in Back of the Envelope Reasoning , 2005, AAAI.

[23]  Luo Si,et al.  A probabilistic graphical model for joint answer ranking in question answering , 2007, SIGIR.

[24]  S. Morrison,et al.  TWO Heads are Better than One , 2011, The Two-Minute Puzzle Book.

[25]  Sanda M. Harabagiu,et al.  Advances in Open Domain Question Answering , 2007 .

[26]  Koby Crammer,et al.  Confidence-weighted linear classification , 2008, ICML '08.

[27]  K. Fernow.  New York , 1896, American Potato Journal.