IBM Watson 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! games.
%0 Journal Article
%1 EpsteinSchorEtAl12ibmjrd
%A Epstein, Edward A.
%A Schor, Marshall I.
%A Iyer, Bhavani
%A Lally, Adam
%A Brown, Eric W.
%A Cwiklik, Jaroslaw
%D 2012
%J IBM Journal of Research and Development
%K 01801 ieee paper ibm ai language processing answer system engineering optimize zzz.iui
%N 3/4
%P 15:1--15:12
%R 10.1147/JRD.2012.2188761
%T Making Watson Fast
%V 56
%X IBM Watson 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! games.
@article{EpsteinSchorEtAl12ibmjrd,
abstract = {IBM Watson 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! games.},
added-at = {2017-11-13T14:45:01.000+0100},
author = {Epstein, Edward A. and Schor, Marshall I. and Iyer, Bhavani and Lally, Adam and Brown, Eric W. and Cwiklik, Jaroslaw},
biburl = {https://www.bibsonomy.org/bibtex/2eed32187afc341827b80821b0451f845/flint63},
doi = {10.1147/JRD.2012.2188761},
file = {IEEE Digital Library:2012/EpsteinSchorEtAl12ibmjrd.pdf:PDF},
groups = {public},
interhash = {e5f7fa606eb8819b359690439e0f7a81},
intrahash = {eed32187afc341827b80821b0451f845},
issn = {0018-8646},
journal = {IBM Journal of Research and Development},
keywords = {01801 ieee paper ibm ai language processing answer system engineering optimize zzz.iui},
number = {3/4},
pages = {15:1--15:12},
timestamp = {2018-04-16T12:41:26.000+0200},
title = {Making {Watson} Fast},
username = {flint63},
volume = 56,
year = 2012
}