A Word Sense Disambiguation Model for Amharic Words using Semi-Supervised Learning Paradigm

Journal Title: STAR Journal - Year 2014, Vol 3, Issue 3

Abstract

The main objective of this research was to design a WSD (word sense disambiguation) prototype model for Amharic words using semi-supervised learning method to extract training sets which minimizes the amount of the required human intervention and it can produce considerable improvement in learning accuracy. Due to the unavailability of Amharic word net, only five words were selected. These words were atena (አጠና), derese (ደረሰ), tenesa (ተነሳ), bela (በላ) and ale (አለ). A separate data sets using five ambiguous words were prepared for the development of this Amharic WSD prototype. The final classification task was done on fully labelled training set using Adaboost, bagging, and AD tree classification algorithms on WEKA package.

Authors and Affiliations

Getahun Wassie| College of Engineering and Technology, Wollega University, Post Box No: 395, Nekemte, Ethiopia, Ramesh Babu P| College of Engineering and Technology, Wollega University, Post Box No: 395, Nekemte, Ethiopia, Solomon Teferra| School of Information Science, Addis Ababa University, Post Box No: 1176, Addis Ababa, Ethiopia, Million Meshesha| School of Information Science, Addis Ababa University, Post Box No: 1176, Addis Ababa, Ethiopia

Keywords

Related Articles

Mathematical Modelling of Thermal Degradation Kinetics of Ascorbic Acid in Brassica Carinata

Ethiopian green collard (Brassica Carinata) locally named yeabesha gomen is one of the important vegetable for ascorbic acid source in our society. However, adequate study has not been conducted to exploit the potential...

Development and Application of Spatially Parameterized Depth Duration Frequency Model for Estimation of Design Rainfall for Oromia State, Ethiopia

The magnitude and frequency of extreme rainfall events are required for planning, design and operation of many hydrological and water resources projects. Design rainfall depth is often used to estimate the severity and...

Homemade Products and Socio-Cultural Values of Wheat Seed Production in Ambo and Dandi Districts of West Central Ethiopia

The objective of the study was to document homemade dishes/beverages from wheat landraces and socio-cultural lifestyles of people related to wheat production in Ambo and Dandi Districts, West Shewa. A total of four Pea...

Occurrence of Gastrointestinal Helminths in rabbits with special Reference to Importance of Giardia spp. as Parasitic Zoonoses

The aim of this study was to detect Giardia spp. as zoonotic helminth as Giardiosis has been recognised as the one of the important parasitic diarrhoea among children as cross transmission may occur between human and r...

Validated Stability Indicating RP-HPLC Method for Simultaneous Estimation of Ofloxacin and Cefixime in their Combined Dosage Form

The objective of the current study was to develop and validate a simple, accurate, precise and selective stability-indicating gradient reverse phase high performance liquid chromatographic method for simultaneous estim...

Download PDF file
  • EP ID EP9698
  • DOI http://dx.doi.org/10.4314/star.v3i3.25
  • Views 329
  • Downloads 15

How To Cite

Getahun Wassie, Ramesh Babu P, Solomon Teferra, Million Meshesha (2014). A Word Sense Disambiguation Model for Amharic Words using Semi-Supervised Learning Paradigm. STAR Journal, 3(3), 147-155. https://europub.co.uk/articles/-A-9698