Induction of Root and Pattern Lexicon for Unsupervised Morphological Analysis of Arabic
Year: 2013
Type: article
Abstract: We propose an unsupervised approach to learning non-concatenative morphology, which we apply to induce a lexicon of Arabic roots and pattern templates. The approach is based on the idea that roots and patterns may be revealed through mutually recursive scoring based on hypothesized pattern and root frequencies. After a further iterative refinement stage, morphological analysis with the induced lexicon achieves a root identification accuracy of over 94%. Our approach differs from previous work on unsupervised learning of Arabic morphology in that it is applicable to naturally-written, unvowelled text. 1
Authors: Bilal Khaliq, John Carrol
Institution: University of Sussex
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W351507719