Making Watson fast

被引:22
作者
Epstein, E. A. [1 ]
Schor, M. I. [1 ]
Iyer, B. S. [1 ]
Lally, A. [1 ]
Brown, E. W. [1 ]
Cwiklik, J. [1 ]
机构
[1] IBM Corp, Div Res, Thomas J Watson Res Ctr, Yorktown Hts, NY 10598 USA
关键词
Application programs - Natural language processing systems;
D O I
10.1147/JRD.2012.2188761
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
IBM Watson (TM) is a system created to demonstrate DeepQA technology by competing against human champions in a question-answering game designed for people. The DeepQA architecture was designed to be massively parallel, with an expectation that low latency response times could be achieved by doing parallel computation on many computers. This paper describes how a large set of deep natural-language processing programs were integrated into a single application, scaled out across thousands of central processing unit cores, and optimized to run fast enough to compete in live Jeopardy!(TM) games.
引用
收藏
页数:12
相关论文
共 6 条
[1]  
[Anonymous], IBM J RES DEV
[2]  
Carroll J. Chu-, 2002, P 11 TEXT RETR C
[3]   Automatic knowledge extraction from documents [J].
Fan, J. ;
Kalyanpur, A. ;
Gondek, D. C. ;
Ferrucci, D. A. .
IBM JOURNAL OF RESEARCH AND DEVELOPMENT, 2012, 56 (3-4)
[4]   Introduction to "This is Watson" [J].
Ferrucci, D. A. .
IBM JOURNAL OF RESEARCH AND DEVELOPMENT, 2012, 56 (3-4)
[5]  
Girju R, 2003, HLT-NAACL 2003: HUMAN LANGUAGE TECHNOLOGY CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, PROCEEDINGS OF THE MAIN CONFERENCE, P80
[6]  
Murdock J. W., 2012, IBM J RES DEV, V56, P8