Using regularization techniques, we limit the amount of information encoded in latent embeddings, creating cleaner embeddings which better align with the latent variables we are modelling.
Our main goal is to develop fact checking algorithms that can assess the credibility of claims mentioned in the textual statements and provide interpretable valid evidence that explains why a certain claim is considered as factually true or fake.
Our main goal is to automatically search for relevant answers among many responses provided for a given question (Answer Selection), and search for relevant questions to reuse their existing answers (Question Retrieval).
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.
Multi-robot path planning for robot swarms that can both fly and drive
Fairness in computer vision
In our work we developed a model that is able to synthesize many probable future frames with just a single image as input.
Transitioning machine learning models across electronic health record (EHR) versions can be improved by mapping different EHR encodings to a common vocabulary.
We develop machine learning algorithms to automatically and quantitatively assess the severity of pulmonary edema from chest x-ray images.
Using adversarial signals and a cycle-consistency based regularization, we can supplement paired regression tasks with unpaired data to improve regression performance.