The Arabic language is spoken by over one billion people around the world. Arabic presents a variety of challenges for speech and language processing technologies. In our group, we have several research topics examining Arabic, including dialect identification, speech recognition, machine translation, and language processing.

Fact Checking in Arabic: As an attempt to oppose the constantly growing spread of online fake news, we aim to develop a fully-automated fact checking system; Given a claim written in Arabic, the system checks knowledge sources (e.g., the Web) and selects related evidence in order to confirm or reject that claim. This involves modeling agreement (stance) between the evidence and the claim, modeling the credibility of the sources (as well as other indicators to truthfulness), developing the necessary resources and datasets, which is extremely important in a low-resource language as Arabic, and finally handling the linguistic and morphological complexity of Arabic. This project is part of the QCRI-CSAIL collaboration.