Ahmad Sait

Artificial Intelligence Specialization · Cohort 2025

Multi-Task Contrastive Learning for Multimodal Soccer Foul Retrieval

A Retrieval system that retrieves past foul verdicts to help referees make a decision on a similar present one

Read the final report (PDF)

See it in the program report (PDF)

Artificial Intelligence Specialization · Cohort 2023

Language Translator: Arabic Sign Language Translator

The "Real-Time Arabic Sign Language Translator” is an AI project that utilizes the YOLO v5 detection model and custom training data to accurately recognize and translate Arabic sign language gestures in real-time. This project aims to bridge the communication gap between individuals with hearing impairments and those who do not understand sign language, empowering them and fostering inclusivity. The report provides an overview of the project, including motivations, background, and technical details.

See it in the program report (PDF)

Artificial Intelligence Specialization · Cohort 2023

Hunayn: Elevating Translation Beyond the Literal

Hunayn is an advanced English-to-Arabic translator surpassing conventional tools. Leveraging the Helsinki transformer (MarianMT), our approach involves fine-tuning on a self-scraped, purely literary Arabic dataset. Evaluations against Google Translate show consistent outperformance in BLEU scores and qualitative assessments. Notably, it excels in cultural sensitivity and context accuracy. This research underscores the Helsinki transformer's superiority for English-to-Arabic translation using a Fus’ha dataset.

See it in the program report (PDF)