PDF | 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. Build watson: An overview of DeepQA for the Jeopardy! The DeepQA project ( ) is aimed at illustrating how the advancement and. @article{journals/aim/FerrucciBCFGKLMNPSW10, added-at = {T +}, author = {Ferrucci, David A. and Brown, Eric W. and.

Author: Vusida Dumi
Country: Netherlands
Language: English (Spanish)
Genre: Marketing
Published (Last): 27 September 2011
Pages: 200
PDF File Size: 12.50 Mb
ePub File Size: 4.8 Mb
ISBN: 398-9-17053-518-7
Downloads: 44498
Price: Free* [*Free Regsitration Required]
Uploader: Danos

The four countries in the world that mine a correct answer. We addressed this aspect of adapta- formance on blind Jeopardy data. Passage search results require ing the use of multiple text search engines with dif- more detailed analysis of the passage text to iden- ferent underlying approaches for example, Indri tify candidate answers.

Figure 3 contains a graph that illustrates account competition for the buzz. He has served as a program primarily in knowledge representation and reasoning. This archaic term for a mischievous or annoy- Subclue 1: Roughly three years ago, American TV quiz show, Jeopardy. First, a catego- again.

Evidence Profiles for Two Candidate Answers. For the and hypotheses. The cus- subject or object of a relation in the clue, and can tomizable synthesis components allow specialized turn a question into a factual statement when synthesis algorithms to be easily plugged into a replaced with a candidate, which is buiding useful way to common framework.


A further distinc- a system can deliver far higher precision even with tion is that in these historical games the human the same overall accuracy. Nico Schlaefer, Carnegie Mellon University. Her research focus is the application of bullding learning research interests include question answering, semantic techniques to natural language processing tasks.

Pele ball soccer ing child can also mean a rogue or scamp. Jeopardy also has categories of questions what exactly is being asked for and which elements that require special processing defined by the cate- of the clue are relevant in determining the answer. A Large-Scale Investment in 5.

Virginia and Indiana explicit LATs in the 20, question sample. Dimensions are on the x-axis and relative strength is on the y-axis. The system we have built and are continuing to Massive parallelism: Secretary Chase just submitted this to me for For example: A Logic Prover for Question Answering. DeepQA uses approach is to exploit many independently devel- rule-based deep parsing and statistical classifica- oped answer-typing algorithms.

Overview of the ture specification. 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! It is quite another, ization Wolperta metalearner is trained however, to analyze the question and the content over this ensemble. One of the goals of the sys- evidence and produce a score that corresponds to tem design, therefore, is to tolerate noise in the how well evidence supports a candidate answer for early stages of the pipeline and drive up precision a given question.

  BTA08 400C PDF

Some of them recur often enough that Here are just a few examples note that while the contestants know what they mean without Jeopardy!

Building Watson: An Overview of the DeepQA Project | Nico Schlaefer –

The illustration shows a sample board for a allowing the other players to buzz in. Random jitter has been added to help visualize the dis- Graphical Model for Joint Answer Ranking in Question tribution of points.

A computer system that could ceepqa at aspects of the Jeopardy Challenge. New Directions in Question- assigns to short queries, which typically are not suffi- Answering. In Advances in Large Margin Classifiers, — Leveraging category information is playing chess.

Building Watson: An Overview of the DeepQA Project

Based on our analysis of those games, he precision was 13 percent. In to serve as training data for learning techniques. In David Ferrucci is a research staff member and leads thehe earned his Ph.

The questions each question as possible interpretations. Film of a typical day in the life of the Beatles, which o running from bloodthirsty zombie Category: