An Artificial Neural Network Approach for Sentence Boundary Disambiguation in Urdu Language Text

An Artificial Neural Network Approach for Sentence Boundary Disambiguation in Urdu Language Text

Shazia Raj, Zobia Rehman, Sonia Rauf, Rehana Siddique, and  Waqas Anwar

Department of Computer Science, COMSATS Institute of Information Technology, Pakistan

Abstract: Sentence boundary identification is an important step for text processing tasks, e.g., machine translation, POS tagging, text summarization etc., in this paper we present an approach comprising of feed forward neural network along with part of speech information of the words in a corpus. Proposed adaptive system has been tested after training it with varying sizes of data and threshold values. The best results, our system produced are 93.05% precision, 99.53% recall and 96.18% f-measure.

Keywords: Sentence boundary identification, feed forwardneural network, back propagation learning algorithm.

Received April 22, 2013; accepted September 19, 2013

Full text


 

Read 2280 times Last modified on Sunday, 19 August 2018 04:55
Share

Upcoming courses

  • Diploma Courses
  • Business and Enterprise
  • Digital Literacy & IT
  • Health Literacy
  • Business Literacy

Free courses

Starting from Jun. 14 2016

the degree finder

in 3 easy steps
Top
We use cookies to improve our website. By continuing to use this website, you are giving consent to cookies being used. More details…