View Full Document

USING SEMANTIC REPRESENTATIONS IN QUESTION ANSWERING



View the full content.
View Full Document
View Full Document

11 views

Unformatted text preview:

USING SEMANTIC REPRESENTATIONS IN QUESTION ANSWERING Sameer S Pradhan Valerie Krugler Wayne Ward Dan Jurafsky and James H Martin Center for Spoken Language Research University of Colorado Boulder CO 80309 0594 USA ABSTRACT This paper describes the architecture of a Question Answering system for answering complex questions that require the integration of various techniques such as Robust Semantics Event Detection Information Fusion and Summarization The focus of the paper is on a general Semantic Representation and how it can be used in the question answering process We describe the vision for the system report on its current state of development and evaluate its accuracy on TREC 9 and TREC 10 questions We also discuss a confidence annotation scheme and evaluate it using the NIST scoring metric 1 INTRODUCTION The Center for Spoken Language Research CSLR at the University of Colorado and Columbia University are collaborating to develop a new technology for question answering This project is supported by the ARDA AQUAINT Advanced QUestion and Answering for INTelligence program The project proposes to integrate robust semantics event detection information fusion and summarization technologies to enable a multimedia question answering system The goal is to develop a system capable of answering complex questions these are questions that require interacting with the user to refine and clarify the context of the question whose answer may be located in non homogeneous databases of speech and text and for which presenting the answer requires combining and summarizing information from multiple sources and over time Generating a satisfactory answer to complex questions requires the ability to collect all relevant answers from multiple documents in different media weigh their relative importance and generate a coherent summary of the multiple facts and opinions reported We propose to integrate four core technologies Semantic annotation CSLR We use a shallow domain independent



Access the best Study Guides, Lecture Notes and Practice Exams

Loading Unlocking...
Login

Join to view USING SEMANTIC REPRESENTATIONS IN QUESTION ANSWERING and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view USING SEMANTIC REPRESENTATIONS IN QUESTION ANSWERING and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?