Improving POS Tagging for Arabic Dialects on Out-of-Domain Texts

Noor Abo Mokh, Daniel Dakota, Sandra Kübler


Abstract
We investigate part of speech tagging for four Arabic dialects (Gulf, Levantine, Egyptian, and Maghrebi), in an out-of-domain setting. More specifically, we look at the effectiveness of 1) upsampling the target dialect in the training data of a joint model, 2) increasing the consistency of the annotations, and 3) using word embeddings pre-trained on a large corpus of dialectal Arabic. We increase the accuracy on average by about 20 percentage points.
Anthology ID:
2022.wanlp-1.22
Volume:
Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates (Hybrid)
Editors:
Houda Bouamor, Hend Al-Khalifa, Kareem Darwish, Owen Rambow, Fethi Bougares, Ahmed Abdelali, Nadi Tomeh, Salam Khalifa, Wajdi Zaghouani
Venue:
WANLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
238–248
Language:
URL:
https://aclanthology.org/2022.wanlp-1.22
DOI:
10.18653/v1/2022.wanlp-1.22
Bibkey:
Cite (ACL):
Noor Abo Mokh, Daniel Dakota, and Sandra Kübler. 2022. Improving POS Tagging for Arabic Dialects on Out-of-Domain Texts. In Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP), pages 238–248, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
Cite (Informal):
Improving POS Tagging for Arabic Dialects on Out-of-Domain Texts (Abo Mokh et al., WANLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.wanlp-1.22.pdf