• Publications
  • Influence
UIMA: an architectural approach to unstructured information processing in the corporate research environment
TLDR
In this paper we give a general introduction to UIMA focusing on the design points of its analysis engine architecture and we discuss how UIM a is helping to accelerate research and technology transfer. Expand
  • 961
  • 120
Building Watson: An Overview of the DeepQA Project
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 show, Jeopardy! The extent of the challenge includesExpand
  • 1,290
  • 86
  • PDF
Building an example application with the Unstructured Information Management Architecture
TLDR
IBM's Unstrutured Information Management Architecture is a software architecture for developing and deploying unstructured information management applications. Expand
  • 164
  • 14
Question analysis: How Watson reads a clue
TLDR
The first stage of processing in the IBM Watson™ system is to perform a detailed analysis of the question in order to determine what it is asking for and how best to approach answering it. Expand
  • 156
  • 11
  • PDF
A framework for merging and ranking of answers in DeepQA
TLDR
The final stage in the IBM DeepQA pipeline involves ranking all candidate answers according to their evidence scores and judging the likelihood that each candidate answer is correct. Expand
  • 85
  • 11
  • PDF
Structured data and inference in DeepQA
TLDR
We present details of appropriate components and demonstrate their end-to-end impact on the IBM Watsoni system. Expand
  • 77
  • 1
  • PDF
Towards the Open Advancement of Question Answering Systems December 2008
David Ferrucci1, Eric Nyberg2, James Allan3, Ken Barker4, Eric Brown1, Jennifer Chu-Carroll1, Arthur Ciccolo1, Pablo Duboue1, James Fan1, David Gondek1, Eduard Hovy5, Boris Katz6, Adam Lally1,Expand
  • 27
  • 1
  • PDF
Identifying implicit relationships
TLDR
Answering natural-language questions may often involve identifying hidden associations and implicit relationships. Expand
  • 19
  • 1
  • PDF
Fact-based question decomposition for candidate answer re-ranking
TLDR
Factoid questions often contain one or more assertions (facts) about their answers. Expand
  • 11
  • 1
  • PDF
Textual evidence gathering and analysis
One useful source of evidence for evaluating a candidate answer to a question is a passage that contains the candidate answer and is relevant to the question. In the DeepQA pipeline, we retrieveExpand
  • 55
  • PDF
...
1
2
3
...