An OpenNMT Model to Arabic Broken Plurals

Elsayed Issa


Abstract
Arabic Broken Plurals show an interesting phenomenon in Arabic morphology as they are formed by shifting the consonants of the syllables into different syllable patterns, and subsequently, the pattern of the word changes. The present paper, therefore, attempts to look at Arabic broken plurals from the perspective of neural networks by implementing an OpenNMT experiment to better understand and interpret the behavior of these plurals, especially when it comes to L2 acquisition. The results show that the model is successful in predicting the Arabic template. However, it fails to predict certain consonants such as the emphatics and the gutturals. This reinforces the fact that these consonants or sounds are the most difficult for L2 learners to acquire.
Anthology ID:
W18-4103
Volume:
Proceedings of the First International Workshop on Language Cognition and Computational Models
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Editors:
Manjira Sinha, Tirthankar Dasgupta
Venue:
LCCM
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
22–30
Language:
URL:
https://aclanthology.org/W18-4103
DOI:
Bibkey:
Cite (ACL):
Elsayed Issa. 2018. An OpenNMT Model to Arabic Broken Plurals. In Proceedings of the First International Workshop on Language Cognition and Computational Models, pages 22–30, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
An OpenNMT Model to Arabic Broken Plurals (Issa, LCCM 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-4103.pdf