The CMU-Q project aims to draw an interactive map of the Qatari dialect

A research team from Carnegie Mellon University in Qatar (CMU-Q), a partner university of the Qatar Foundation, is working on the exploration and analysis of dialects in Qatar.
“Our main goal is to expand Qatar’s knowledge base with respect to Qatari dialect, heritage, culture and identity,” says Zeinab Ibrahim, Teaching Professor of Arabic Studies and Principal Researcher of the Creation Project. an interactive map of the Qatari dialect.
The project is funded by the National Priorities Research Program of the Qatar National Research Fund (QNRF).
Principal investigators include Houda Bouamor, assistant professor of information systems education at CMU-Q, as well as Aisha Sultan from Doha International Family Institute and Hany Abdelrhem from Georgetown University in Qatar.
For the project, the research team traces the social and geographic variations of the Qatari dialect over generations and creates a digital tool to explore pronunciation, usage and expressions.
Ibrahim believes CMU-Q’s research can help preserve and promote Arabic language learning in Qatar. “I’ve been living in Qatar for quite a while now, and noticed a lack of references on the local dialect which has changed over the years. Also, a lot of people are moving and working here, and would like to learn the Qatari dialect , but there is no reference or manual available for it,” she says.
“Thus, the result of this research effort can be used to develop programs that help Qatari students learn Standard Arabic.”
Bouamor is working on the second part of the project: evaluating the use of the Qatari dialect from a computational linguistic point of view. “Looking at the way people write on social media, for example, we notice that they use either English or the Qatari dialect. It is therefore important to establish references of the linguistic resources used. Dialects differ from country to country, even within the Arabian Gulf.The Emirati dialect differs from the Kuwaiti dialect, for example.Therefore, we need to conduct real research to determine whether there is a general Gulf dialect or whether each country has its own specific dialect.
“We see that many people over the age of 60, for example, use different language expressions than those used by young people in their twenties. We must therefore monitor these changes, and draw up a reference map.”
As part of efforts to develop an interactive linguistic map of the Qatari dialect, the research team is working on collecting data from native speakers and collecting linguistic vocabulary in its basic form.
With the participation of Qatari researchers, the project features interviews with Qatari individuals with the aim of establishing standard written conventions for the Qatari dialect, and digitizing and analyzing this information using language processing techniques. natural and machine learning.
Hamed al-Qahtani is a research assistant on the project and represents the Bedouin dialect. “As part of our work, we had to conduct interviews with people of different ages addressing five specific themes relating to heritage and ancient customs and their evolution over time, as well as the nature of past work and unlike the past and the We also asked participants about their views on contemporary issues, such as Qatar hosting the World Cup.”
The research effort nonetheless faced several challenges, the biggest of which was gaining people’s confidence to speak naturally and spontaneously, says Delma al-Hajri, another research assistant. “Among the difficulties we have encountered is the reluctance of some people to participate in the interviews. Some were not interested in the subject or did not want the conversation to be recorded for reasons of confidentiality, although they were assured that the information would be used for research purposes only.”
The research project also provides a valuable resource that can be leveraged to create different tools that automatically process the Qatari dialect, starting with creating the linguistic map of Qatar, explains Bouamor.
“From a computational perspective, this is a great resource. For example, we can draw a map showing where specific words are most commonly used, which is one of the key goals of this project. From a neurolinguistic programming perspective, we can build a morphological analysis tool using machine learning.Another application is to build machine translation systems or tools to search for documents and information using a purely local dialect.