Phd in CIVILIZATIONS OF ASIA AND AFRICA

Thesis title: Tunisian Arabizi: Linguistic Analyses and Corpus Building using Natural Language Processing

This thesis is about a project focused on Tunisian Arabic encoded in Arabizi, the Latin-based writing system for digital conversations. The project led to the creation of two integrated and independent tools to provide a response to the lack of tools to support research on Tunisian Arabic: a linguistic corpus and a neural network architecture created to annotate the former with various levels of linguistic information (word classification, transliteration, tokenization, POS-tagging, lemmatization). The thesis discusses the choices made in terms of computational and linguistic methodology and the strategies adopted to improve our computational results. In addition, the analyses performed on our corpus data, in order to investigate Tunisian Arabizi, will be outlined.