Towards Comprehensive Computational Representations of Arabic Multiword Expressions

A successful computational treatment of multiword expressions (MWEs) in natural languages leads to a robust NLP system which considers the long-standing problem of language ambiguity caused primarily by this complex linguistic phenomenon. The first step in addressing

this challenge is building an extensive reliable MWEs language resource LR with comprehensive computational representations across all linguistic levels. This forms the cornerstone in understanding the heterogeneous linguistic behaviour of MWEs in their various manifestations. This paper presents a detailed framework for computational representations of Arabic MWEs (ArMWEs) across all linguistic levels based on the state-of-the-art lexical mark-up framework (LMF) with the necessary modifications to suit the distinctive properties of Modern Standard Arabic (MSA). This work forms part of a larger project that aims to develop a comprehensive computational lexicon of ArMWEs for NLP and language pedagogy LP (JOMAL project).