| Share this Session: |
|
Aditya Kalyanpur Research Staff Member IBM |
|
Tuesday, June 7, 2011
Over the past four years a team of IBM Research scientists set out to accomplish a grand challenge: build a computing system that rivals a human's ability to answer questions posed in natural language with speed, accuracy and confidence, while analyzing subtle meaning and other complexities in which humans excel and computers traditionally do not. The DeepQA project at IBM is designed to tackle this challenge, with the aim being to explore how advancing and integrating Natural Language Processing (NLP), Information Retrieval (IR), Machine Learning (ML), Knowledge Representation and Reasoning (KR&R) and massively parallel computation can greatly advance open-domain automatic Question Answering. In this talk, I will give an overview of the DeepQA technology and describe how it was used to build Watson, the computer system that won the Jeopardy! Challenge in February 2011. Watson's ability to process and analyze vast amounts of unstructured data has the potential to transform business intelligence, healthcare, customer support, enterprise knowledge management, social computing, science and government.
Aditya Kalyanpur is a Research Staff Member at IBM Watson. His research interests include knowledge representation & reasoning (ontologies, Semantic Web), natural language processing, machine learning and statistical data mining.
Aditya is currently a member of the DeepQA team that is advancing the state-of-the-art in automatic, open-domain question answering. The DeepQA technology is used in the Watson system, which won the Jeopardy! Man vs. Machine challenge in February 2011. Aditya has been involved in the development of several core algorithms in Watson related to question analysis, evidence gathering and scoring, knowledge based inference, and answer merging and ranking.
Previously, Aditya worked on the Scalable Highly Expressive Reasoner (SHER) project at IBM, a breakthrough semantic search technology that scales to very large and expressive logic-based knowledge bases. SHER has been successfully deployed in semantic search applications, especially in the medical domain.
|
|||||||||
