Resource-limited and morphologically rich languages pose many challenges to natural language processing tasks. Their highly inflected surface forms inflate the vocabulary size and increase sparsity in an already scarce data situation. In this article, we present an unsupervised learning approach to vocabulary reduction through morphological segmentation. We demonstrate its value in the context of machine translation for dialectal Arabic (DA), the primarily spoken, orthographically unstandardized, morphologically rich and yet resource poor variants of Standard Arabic. Our approach exploits the existence of monolingual and parallel data. We show comparable performance to state-of-the-art supervised methods for DA segmentation.
Mendeley helps you to discover research relevant for your work.
CITATION STYLE
Salloum, W., & Habash, N. (2022). Unsupervised Arabic dialect segmentation for machine translation. Natural Language Engineering, 28(2), 223–248. https://doi.org/10.1017/S1351324920000455