Question Answering Technology? Sounds Like a Natural (Language) To Me
Who says high-performance computing is a game? Well, researchers at IBM and Carnegie Mellon University among others, at least if the game is the TV quiz show Jeopardy! . That's why in the near future an IBM research project dubbed "Watson" will challenge human quiz-show competitors in a Deep Blue vs. Garry Kasparov like match.
Watson is an outgrowth of the Open Advancement in Question Answering (OAQA) project launched by IBM and CMU, which is itself an off-shoot of an earlier Question Answering (QA) project named PIQUANT, short for "Practical Intelligent QUestion ANswering Technology". Watson is designed to answer questions that require the identification of relevant and irrelevant content, the interpretation of ambiguous expression and puns, the decomposition of questions into sub-questions, and the logical synthesis of final answers. In addition, Watson will compute a statistical confidence in the responses it provides. Watson will be designed to do all of this in a matter of seconds, which will enable it to compete against humans, who have the ability to know what they know in less than a second. To make this possible, Watson incorporates massively parallel analytical capabilities and, just like human competitors, not be connected to the Internet or have any other outside assistance.
<p>Unlike conventional computing technologies designed to return documents containing the user's keywords or semantic entities, Watson is expected to leap ahead to interpret the user's query as a true question and to determine precisely what the user is asking for. Watson uses massively parallel processing to simultaneously and instantly understand complex questions -- questions that require the system to consider huge volumes and varieties of natural language text to gather and then deeply analyze and score supporting or refuting evidence. The system then decides how confident it is in the answer. This approach marries advanced machine learning and statistical techniques with the latest in natural language processing to result in human-like precision and speed, huge breadth and accurate confidence determination.
"The challenge is to build a system that, unlike systems before it, can rival the human mind’s ability to determine precise answers to natural language questions and to compute accurate confidences in the answers," said David Ferrucci, leader of the IBM Watson project team. "This confidence processing ability is key. It greatly distinguishes the IBM approach from conventional search, and is critical to implementing useful business applications of Question Answering."
IBM's effort to create Watson is aimed at exploring the future of business intelligence, analytics and information management.