Meeting and Lecture Translation
Description
The meeting and lecture translation project aims to tackle the challenges of spoken translation in spontaneous situations where there are: 1) multiple speakers (meetings) and 2) single speakers but highly technical content (lectures).
Demos
-
Meeting Translation system
A Web-based multi-party spoken translation system for Arabic-English meetings. -
QED Educational corpus
An open multilingual collection of subtitles for educational videos and lectures collaboratively transcribed and translated over the AMARA web-based platform.
Achievements
- December 2013Winner of the Arabic-English and English-Arabic tracks in IWSLT translation shared-task.
- June 2015Runner-up at the Arabic-English track at NIST 2015.
- April 2014Collected and shared the QED (Amara) Parallel Corpus for the Educational Domain
Related Publications
The QCN Egyptian Arabic to English Statistical Machine Translation System for NIST OpenMT’2015
Hassan Sajjad, Nadir Durrani, Francisco Guzmán, Preslav Nakov, Ahmed Abdelali, Stephan Vogel, Wael Salloum, Ahmed El Kholy, Nizar Habash. In Proceedings of the NIST Open Machine Translation Evaluation Workshop 2015.
PDF Abstract BibTex Slides
Hassan Sajjad, Nadir Durrani, Francisco Guzmán, Preslav Nakov, Ahmed Abdelali, Stephan Vogel, Wael Salloum, Ahmed El Kholy, Nizar Habash. In Proceedings of the NIST Open Machine Translation Evaluation Workshop 2015.
PDF Abstract BibTex Slides
The AMARA Corpus: Building parallel language resources for the educational domain
Ahmed Abdelali, Francisco Guzmán, Hassan Sajjad, and Stephan Vogel. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14) 2014.
PDF Abstract BibTex Slides
Ahmed Abdelali, Francisco Guzmán, Hassan Sajjad, and Stephan Vogel. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14) 2014.
PDF Abstract BibTex Slides
Amara: A Sustainable, Global Solution for Accessibility, Powered by Communities of Volunteers
Dean Jansen, Aleli Alcala, and Francisco Guzmán. In Universal Access in Human-Computer Interaction. Design for All and Accessibility Practice, pages 401-411, 2014.
PDF Abstract BibTex
Dean Jansen, Aleli Alcala, and Francisco Guzmán. In Universal Access in Human-Computer Interaction. Design for All and Accessibility Practice, pages 401-411, 2014.
PDF Abstract BibTex
QCRI at IWSLT 2013: Experiments in Arabic-English and English-Arabic Spoken Language Translation
Hassan Sajjad, Francisco Guzmán, Preslav Nakov, Ahmed Abdelali, Kenton Murray, Fahad Al Obaidli, and Stephan Vogel. In Proceedings of the 10th International Workshop on Spoken Language Translation (IWSLT'13) 2013.
PDF Abstract BibTex Slides
Hassan Sajjad, Francisco Guzmán, Preslav Nakov, Ahmed Abdelali, Kenton Murray, Fahad Al Obaidli, and Stephan Vogel. In Proceedings of the 10th International Workshop on Spoken Language Translation (IWSLT'13) 2013.
PDF Abstract BibTex Slides
The AMARA Corpus: Building Resources for Translating the Web's Educational Content
Francisco Guzmán, Hassan Sajjad, Ahmed Abdelali, and Stephan Vogel. In Proceedings of the 10th International Workshop on Spoken Language Translation (IWSLT'13) 2013.
PDF Abstract BibTex Slides
Francisco Guzmán, Hassan Sajjad, Ahmed Abdelali, and Stephan Vogel. In Proceedings of the 10th International Workshop on Spoken Language Translation (IWSLT'13) 2013.
PDF Abstract BibTex Slides