Syntactic Sentence Fusion Techniques for Bengali
Journal Title: International Journal of Computer Science and Information Technologies - Year 2011, Vol 2, Issue 1
Abstract
The present paper describes various syntactic sentence fusion techniques for Bengali language that belongs to the Indo-Aryan language family. Firstly a clause identification and classification system marks clause boundaries and classifies them as principle clause and subordinate clauses. A rule-based sentence classification system has been developed to categorize sentences as simple, complex and compound. The final syntactic sentence fusion system makes use of the sentence class and the clause types and finally fuses two textually entailed sentences using verb paradigm information and noun morphological information. The system outputs are compared with a gold standard data set using manual evaluation and BLEU techniques. The evaluation results yield good accuracy scores. The syntactic sentence fusion technique developed in the present work may be applied for other Indian languages.
Authors and Affiliations
Amitava Das , Sivaji Bandyopadhyay
Keywords
Related Articles
- EP ID EP134448
- DOI -
- Views 112
- Downloads 0
A NOVEL APPROACH FOR RETRIEVING AN IMAGE USING CBIR
In this paper we mainly focussed on how to retreive the images from large database. Generally in huge databases we will have large number of images with the same name. when we want to retrieve the image by giving a name,...
Performance issues on AODV and AOMDV for MANETS
One of the main challenges of MANET is the design of robust routing algorithms that adapt to the frequent and randomly changing network topology. A variety of routing protocols have been proposed and...
Detection of Abnormal Masses in Mammogram Images
Masses in the breast can be located in digital mammogram images by computationally analysing various feature statistics from the image. Any algorithm used to analyse digital mammogram images can be both time-consuming an...
Outlier Detection for Multidimensional Medical Data
The knowledge-rich nature of the Medical Information domain has made it an ideal environment where knowledge on data mining should have to be unearthed from large data collection for dialysis’ of growing unknown diseases...
Selecting type of clusters that are most appropriate for capturing overlapping interests of different types of users in personalization tasks using Web Usage Mining
Clustering is one of the most important phase of the web personalization, so selecting proper types of cluster to justify the user interest for creating user profile is again very important. In this paper, we address th...