Noor Abo Mokh


Improving POS Tagging for Arabic Dialects on Out-of-Domain Texts
Noor Abo Mokh | Daniel Dakota | Sandra Kübler
Proceedings of the The Seventh Arabic Natural Language Processing Workshop (WANLP)

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.