Graduate Thesis Builds a Corpus for the Palestinian Dialect

New graduate work at Birzeit University has taken a giant leap towards documenting and understanding the Palestinian dialect. MA candidate Diyam Akra recently defended her thesis, which was a collaboration with Sina Institute for Knowledge Engineering and Arabic Technologies and developed under the supervision of Mustafa Jarrar. The thesis is part of the ongoing project Curras funded by the Palestinian Ministry of Higher Education’s Scientific Research Council.

Akra’s thesis discussed linguistic facts about Palestinian dialects and compared them with Modern Standard Arabic in terms of morphology, orthography and lexicon. It also presented an annotated corpus of the Palestinian dialect with relevant metadata. This was done by collecting Palestinian written text from different resources, using existing resources for Egyptian Arabic to analyze corpus and annotate it, annotating manually a list of words that can’t be analyzed using existing resources, and finally using an existing annotation tool to double-check the annotated corpus.

The thesis discussion committee included Nizar Habash, adjunct professor at the Sina Institute and Associate Professor at New York University- Abu Dhabi, Mahdi Arar, the Dean of the Art Faculty, and Abualseoud Hanani, Assistant Professor in the Engineering and Technology faculty.