Developing a Transition Parser for the Arabic Language

Aref Abu,Essam Hanandeh

doi:10.14569/ijacsa.2016.070924

Abstract

One of the most important Characteristics of the Arabic language is the exhaustive undertaking. Thus, analyzing Arabic sentences is difficult because of the length of sentences and the numerous structural complexities. This research aims at developing an Arabic parser and lexicon. A lexicon has been developed with the goal of analyzing and extracting the attributes of Arabic words. The parser was written by using a top–down algorithm parsing technique with recursive transition network. Then, the parser has been evaluated against real sentences and the outcomes were satisfactory.

Highlights

Natural language processing (NLP), which is considered a field of computer science, artificial intelligence, and computational linguistics, is dealing with the interactions between computers and natural languages
The history of NLP generally started in the 1950s, studies can be traced from periods earlier than that a decade
Information retrieval is one of the natural language processing applications that appears in these definitions

Summary

Introduction

Natural language processing (NLP), which is considered a field of computer science, artificial intelligence, and computational linguistics, is dealing with the interactions between computers and natural languages. Recent research has increasingly focused on unsupervised and semi-supervised learning algorithms These algorithms are able to learn from data that have not been hand-annotated with the desired answers, or use a combination of annotated and non-annotated data. This task is considerably more difficult than supervised learning and typically produces inaccurate results for a given amount of input data. Prior implementations of language-processing tasks typically involved the direct hand coding of large sets of rules. The machine-learning paradigm calls for using general learning algorithms, which are often grounded on statistical inference, to automatically learn such rules through the analysis of large corpora of typical real-world examples. Information retrieval is a selective process by which the desired information is extracted from a store of information called a database [3]

Objectives

Methods

Results