Friday 30 April 2010

Wseas Transactions

New Subscription to Wseas Transactions

The following information was submitted:

Transactions: WSEAS TRANSACTIONS ON COMPUTERS
Transactions ID Number: 89-740
Full Name: Maria Moise
Position: Professor
Age: ON
Sex: Female
Address: 1B, Expozitiei Avenue, code 0121 Bucharest, Sector 1, Romania
Country: ROMANIA
Tel: +40-21-2029504
Tel prefix: +40-21
Fax: +40-21-3183566
E-mail address: maria.moise@rau.ro
Other E-mails: lula_moise_maria@yahoo.com
Title of the Paper: Developing Question Answering (QA) Systems using the Patterns
Authors as they appear in the Paper: Maria Moise, Ciprian Gheorghe, Marilena Zingale
Email addresses of all the authors: maria.moise@rau.ro, 7ciprian@gmail.com, zingale@un.org
Number of paper pages: 12
Abstract: This paper describes a way to use Natural Language Processing (NLP) techniques in order to gain faster access to information from a closed domain. Using traditional graphical user interfaces built as a tree structure, such as menus, determine users to browse irrelevant information. To avoid this, we use one of the major tasks in NLI, Question Answering (QA) and build with Visual FoxPro 9.0 a demonstrating application. We impose restrictions related to the domain of use that of tourist attractions in Romania, and restrictions related to natural language input method. We use tags to represent words or groups of words and patterns to symbolize questions. We use this representation in order to provide to user a non-traditional human-computer interaction. The QA system rely on a database where we store specific information on chosen domain and related data in order to accomplish the task of providing an answer. The answering mechanism uses a knowledge engineering with s!
yntactic and semantic approach. At the end of this paper we discuss the QA System Evaluation.
Keywords: Tag, Pattern, Natural Language Processing, Question Answering.
EXTENSION of the file: .pdf
Special (Invited) Session: Natural Language Processing for Rapid Information
Organizer of the Session: 634-480
How Did you learn about congress:
IP ADDRESS: 93.113.252.21