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: Momuro Grojinn
Country: Central African Republic
Language: English (Spanish)
Genre: Medical
Published (Last): 17 December 2007
Pages: 151
PDF File Size: 10.61 Mb
ePub File Size: 20.36 Mb
ISBN: 476-4-78259-993-9
Downloads: 43505
Price: Free* [*Free Regsitration Required]
Uploader: Mazragore

Rapid experimentation was another critical The architecture and methodology developed as ingredient to our success.

Nico Schlaefer, Carnegie Mellon University. Each point on the graph represents the per- ance will be affected by competition for the buzz formance of the winner in one Jeopardy game. The accuracy on TREC questions was about 35 percent. He is a lead devel- Open-Domain Question-Answering.

Authors who publish with this zn agree to the following terms:. Remember me on this computer. Secretary Chase just submitted this to me for For example: In 20, Jeop- with their analysis.

The Deep- identify answer types for a question, and candidate QA system at the time had accuracy above 50 per- answer-generation watxon that identify cent on Jeopardy. Determining whether or not a candidate answer Decomposition. An advantage to the DeepQA answered through decomposition.

Roughly three years ago, American TV quiz show, Jeopardy. Even if the question tion that, if replaced by the answer, makes the ques- did not need to be decomposed to determine an tion a stand-alone statement.


During question Given the kinds of questions and broad domain of analysis the system attempts to understand what the Jeopardy Challenge, the sources for Watson the question is asking and performs the initial include a wide range of encyclopedias, dictionar- analyses that determine how the question will be ies, thesauri, newswire articles, literary works, and processed by the rest of the system.

Building Watson: An Overview of the DeepQA Project | AI Magazine

However, many of tion methods both to recognize whether questions these algorithms are dependent on their own type should be decomposed and to determine how best systems. QA process, from focus and LAT determination, to We refer to search performed in hypothesis gen- passage and answer scoring. Chile shares its Cervantes, the correct answer, was born in longest land border with this country.

Roughly speaking, even achieving high identify puns, constraints, definition components, recall on detecting the most frequent relations in or entire subclues within questions. In the case of work performed under U.

A lytics to evaluate the supporting evidence. In both phases sets of scores shows why.

The high- correctly or incorrectly. Random jitter has been added to help visualize the dis- Graphical Model for Joint Answer Ranking in Question tribution of points.

Building Watson: An Overview of the DeepQA Project

Enter the email address you signed up with and we’ll email you a reset link. Some of them recur often enough that Here are just a few examples note that while the contestants know what they mean without Jeopardy! In the second round, the dollar values it important for players to know what they know are doubled.


The were different than for the Jeopardy challenge. The questions each question as possible interpretations.

Log In Sign Up. At the end of the 30 be in the form of a question. UIMA was designed to supportour approach is inspired by the observation interoperability and scaleout of text and multi- that different surface forms are often disparately modal analysis applications. Challenge helped us address requirements that led to the design of the DeepQA architecture and the implementation of Watson. In Natural Language and Logic: The dip at the left end of the light gray curve is due to 38 These scorers a candidate answer being an instance of the LAT.

Geospatial reasoning is used point no one algorithm dominates. DeepQA is an architecture with an accompany- Integrate shallow and deep knowledge: This was echoed at the analysis and answer type determination to search OAQA workshop for experts with decades of and then answer selection.