Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Improving accessibility in an automated question-answering system

Improving accessibility in an automated question-answering system Improving Accessibility in an Automated Question-Answering System Silvia Quarteroni University of Trento silvia.quarteroni@disi.unitn.it Abstract We address the problem of accessibility in information retrieval by introducing a Question Answering system able to filter answers based on their reading difficulty. The reading level estimation technique is applicable to any domain and is potentially adjustable to any user category. Introduction Using a computer to answer questions has been a human dream since the beginning of the digital era. A first step towards the achievement of such an ambitious goal is to deal with natural language to enable the computer to understand what its user asks and perform information retrieval. Question Answering (QA) can be interpreted as a sub-discipline of information retrieval with the added challenge of applying sophisticated techniques to identify the complex syntactic and semantic relationships present in text in order to find concise answers. However, a common problem in Question Answering and information retrieval is that in most systems results are created independently of the questioner's characteristics, goals and needs. This is a serious limitation: for instance, a primary school child and a History student may need different answers to the question: When did the Middle Ages begin? So http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM SIGACCESS Accessibility and Computing Association for Computing Machinery

Improving accessibility in an automated question-answering system

Download PDF
8 pages

Loading next page...
 
/lp/association-for-computing-machinery/improving-accessibility-in-an-automated-question-answering-system-ZHte9M3MTj

References (17)

Publisher
Association for Computing Machinery
Copyright
Copyright © 2008 by ACM Inc.
ISSN
1558-2337
DOI
10.1145/1452562.1452563
Publisher site
See Article on Publisher Site

Abstract

Improving Accessibility in an Automated Question-Answering System Silvia Quarteroni University of Trento silvia.quarteroni@disi.unitn.it Abstract We address the problem of accessibility in information retrieval by introducing a Question Answering system able to filter answers based on their reading difficulty. The reading level estimation technique is applicable to any domain and is potentially adjustable to any user category. Introduction Using a computer to answer questions has been a human dream since the beginning of the digital era. A first step towards the achievement of such an ambitious goal is to deal with natural language to enable the computer to understand what its user asks and perform information retrieval. Question Answering (QA) can be interpreted as a sub-discipline of information retrieval with the added challenge of applying sophisticated techniques to identify the complex syntactic and semantic relationships present in text in order to find concise answers. However, a common problem in Question Answering and information retrieval is that in most systems results are created independently of the questioner's characteristics, goals and needs. This is a serious limitation: for instance, a primary school child and a History student may need different answers to the question: When did the Middle Ages begin? So

Journal

ACM SIGACCESS Accessibility and Computing – Association for Computing Machinery

Published: Sep 1, 2008

There are no references for this article.