QATS2 - QCRI Automatic Transcription and Translation System
QATS2 is our translation system for online multimedia content to lower the language barriers and improve the reach of news content. It uses language technologies such Automatic Speech Recognition (ASR), Machine Translation (MT) and Text-to-Speech (TTS) to translate multimedia content in the broadcast news domain. The objective of the system is to enable a native web experience for end users. The demo has been presented in the BBCnewsHack and won the "Best in Show" award.
» Go to page
Farasa Arabic Text Processing Library
Farasa (means “insight” in Arabic), is a fast and accurate text processing toolkit for Arabic text. Farasa consists of a segmentation/tokenization module, POS tagger, Arabic text Diacritizer, and Dependency Parser.
The core component of Farasa is the segmentation/tokenization module which is based on SVM-rank. The linear kernels used in the SVM uses a variety of features and lexicons to rank possible segmentations of a word. The features include: likelihoods of stems, prefixes, suffixes, their combinations; presence in lexicons containing valid stems or named entities; and underlying stem templates.
» Go to page
QATIP - The QCRI Arabic Text Image Processing Tool
This demo showcases our system for document analysis and optical character recognition in scanned Arabic documents. The system is particularly strong in handwriting recognition in historic documents. On the IFN/ENIT database (abcde-s) we outperform the best system so far by over 20% relative in terms of word error rate.
» Go to page
CODRA: A Document-level Discourse Parser for English
This demo showcases a complete discriminative framework for discourse analysis in the RST framework. To get more information about the parser and to download the source code follow this link.
» Go to page
Finding Good Answers in QatarLiving
This is a collaboration with MIT and QatarLiving.
» Go to page
Doha City Browser
Doha City Browser is a project aimed at making navigation around Doha easier by providing people with necessary information like Dining, Shopping and Entertainment etc.
» Go to city browser (Chrome, English)
» Go to city browser (Chrome, Arabic)
» Go to city browser (Mobile, Prototype)