Semi-Automatic Data Annotation, POS Tagging and Mildly Context-Sensitive Disambiguation: the eXtended Revised AraMorph (XRAM)

TL;DR

This paper introduces XRAM, an improved Arabic lexical resource that enhances coverage, disambiguation, and semi-automatic annotation, demonstrating high success in practical testing.

Contribution

XRAM extends AraMorph with probabilistic POS tagging, context-sensitive disambiguation, and semi-automatic lexical expansion, addressing previous limitations.

Findings

High success rate in practical testing

Improved coverage of Classical and contemporary Arabic

Enhanced disambiguation and tagging accuracy

Abstract

An extended, revised form of Tim Buckwalter's Arabic lexical and morphological resource AraMorph, eXtended Revised AraMorph (henceforth XRAM), is presented which addresses a number of weaknesses and inconsistencies of the original model by allowing a wider coverage of real-world Classical and contemporary (both formal and informal) Arabic texts. Building upon previous research, XRAM enhancements include (i) flag-selectable usage markers, (ii) probabilistic mildly context-sensitive POS tagging, filtering, disambiguation and ranking of alternative morphological analyses, (iii) semi-automatic increment of lexical coverage through extraction of lexical and morphological information from existing lexical resources. Testing of XRAM through a front-end Python module showed a remarkable success level.