Morphology-based Entity and Relational Entity Extraction Framework for Arabic

TL;DR

This paper introduces MERF, a framework for extracting entities and relational entities from Arabic texts using morphology-based rules, reducing development time and effort compared to existing methods.

Contribution

The paper presents MERF, a morphology-based extraction framework for Arabic that simplifies rule specification and improves efficiency over traditional rule-based techniques.

Findings

Requires shorter development time

Produces reasonably accurate results

Operates with acceptable runtime overhead

Abstract

Rule-based techniques to extract relational entities from documents allow users to specify desired entities with natural language questions, finite state automata, regular expressions and structured query language. They require linguistic and programming expertise and lack support for Arabic morphological analysis. We present a morphology-based entity and relational entity extraction framework for Arabic (MERF). MERF requires basic knowledge of linguistic features and regular expressions, and provides the ability to interactively specify Arabic morphological and synonymity features, tag types associated with regular expressions, and relations and code actions defined over matches of subexpressions. MERF constructs entities and relational entities from matches of the specifications. We evaluated MERF with several case studies. The results show that MERF requires shorter development time and effort compared to existing application specific techniques and produces reasonably accurate results within a reasonable overhead in run time.