Design and Implementation of Predictive Text Entry Method for Afan Oromo on Mobile Phone
No Thumbnail Available
Date
2013-02
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Addis Ababa University
Abstract
Language is a unique phenomenon that distinguishes man from other living things. It is our primary method of communication with each other, yet very little is understood about how language is acquired when we are infants. A greater understanding in this area would have the potential to improve man machine communication. Word prediction is an important NLP problem in which the correct word is predicted based on a given context. This paper presents a new word prediction approach based on context features and machine learning. The proposed method casts the problem as a learning-classification task by training word predictors with highly discriminating features selected by various feature selection techniques. The contribution of this work lies in the new way of presenting this problem, and the unique combination of a top performer in machine learning, svm, with various feature selection techniques and more. The method is implemented and evaluated using several datasets. The experimental results show clearly that the method is effective in predicting the correct words by using small contexts. For an advanced implementation of predictive text entry via machine learning, a multi-level feature based framework is developed. In order to use as much information as possible, features from the character level, word level, syntax level, and semantic level are included. The program that is capable of automatically inferring a grammar from a Natural Language Corpus is developed. Afan Oromo words can be categorized into “Maqaa”, “Ibsa Maqaa”, “Xumura”, “Ibsa Xumuraa” fi “Firoomsee”. In addition the language has short and long voices that are dealt with vowels and strong and weak voices which are dealt with consonants. Due to these voices, Afan Oromo has long words containing many characters. And also Afan Oromo has got its own structure of writing sentences (Subject + Object+ Verb). Keywords: Word prediction, word completion, machine learning, natural language processing.
Description
Keywords
Word Prediction, Word Completion, Machine Learning, Natural Language Processing