Shaheen is the ALT’s Machine Translation (MT) system. It started as a major endeavor and a key platform for the research group. While statistical approaches were more dominant in the beginning, in the last few years, technology advancements have shifted toward Deep Learning methods. Shaheen is a state-of-the-art Machine Translation system trained using encoder-decoder architecture with attention. Shaheen is integral part of QCRI Speech Translation system.

MOFA Deployment (April 22)

Shaheen was deployed at the Ministry of Foreign Affairs.

Arabic Dialects (Feb 21)

Dialectal Shaheen supporting Egyptian, Levantine and Maghrebi was deployed.

Here’s a news coverage and summary of a chat with Hassan Sajjad on this.

1 Billion Words (March 20)

Shaheen achieves milestone of translating 1 billion words. The news featured at the front page of Gulf times.

Ahmed Abdelali was invited for an interview with Qatar TV.

Innovation Award (March 18)

Our Speech Translation System won the Best Innovation Award at the Annual Research Conference in Doha Qatar.