Carnegie Mellon University
Skip navigation and jump directly to page content

Haitians in Crisis

Developing Translation Tools

Haitian Creole
Scientists at Carnegie Mellon University's Language Technologies Institute (LTI) have publicly released spoken and textual data they've compiled on the Haitian Creole language — giving tools to developers looking to support doctors, nurses and others involved in the relief efforts in Haiti.

Since Carnegie Mellon began to make the data publicly available last week, a team at Microsoft Research has used it to help develop an experimental, web-based system for translating between English and Haitian Creole.

Translators Without Borders, a not-for-profit association based in Paris, plans to distribute a medical triage dictionary to doctors in Haiti once that data has been converted into a human-readable format. LTI researchers, likewise, have begun working on their own translation system for Haitian Creole.

Although French is the official language of Haiti and is spoken by elites, Haitian Creole is the most widely spoken language in Haiti, said Robert Frederking, LTI senior systems scientist. Haitian Creole is based on French, but has evolved substantially since Haitians overthrew the French colonists more than 200 years ago. Word meanings have drifted and the language incorporates some African syntax.

"French speakers can sort of puzzle through it, but Creole isn't penetrable if you don't know French," Frederking said. Few translation resources are available for the language, he added.

The Carnegie Mellon data base for Haitian Creole was created in the late 1990s for Diplomat, a project sponsored by the Defense Advanced Research Projects Agency. The project was headed by Jaime Carbonell, LTI director, and focused on developing portable, speech-to-speech translation devices that could be deployed rapidly for Haitian Creole and other languages of special interest to the Department of Defense. Frederking and Alex Rudnicky, principal systems scientist in the Computer Science Department, served as co-principal investigators.

A prototype Haitian Creole translation system was delivered to the U.S. Army, but "as far as we know, nobody ever field-tested it," Frederking said. The project ended in the late 1990s, but LTI retained the data compiled and produced for the project.

Since the Jan. 12 earthquake, LTI researchers decided to begin work on an updated translation system for Haitian Creole that would incorporate the latest translation technologies. To aid other groups pursuing parallel efforts worldwide, they also opted to release the data publicly at www.speech.cs.cmu.edu/haitian/, making it available with minimal restrictions. In addition to the Diplomat material, other data developed by researchers at LTI and elsewhere are being added to the site as they become available.

Given the extreme poverty of Haiti, "nobody is going to make money on a Haitian Creole translator," Frederking said. "But translation systems could be an important tool, both for the relief workers now involved in emergency response and in the long-term as rebuilding takes place."

LTI, which focuses on such topics as machine translation, speech processing, information retrieval, text mining and computer-assisted language learning, is one of seven academic units in Carnegie Mellon's School of Computer Science.

Photo Caption: U.S. Navy Electronics Technician 1st Class Dietrich Rey provides water to a Haitian child who is being treated aboard the Military Sealift Command hospital ship USNS Comfort (T-AH 20) for a broken leg. Rey is a communications systems manager aboard Comfort but his ability to speak Creole has been valuable to doctors trying to communicate with patients affected by a 7.0 magnitude earthquake that struck the Caribbean nation of Haiti on Jan. 12, 2010. Comfort is working in unison with a multinational force in Operation Unified Response to ease suffering in Haiti by providing food, water and medical care. (U.S. Navy photo by Mass Communication Specialist 3rd Class Timothy Wilson/Released)

Related Links: Language Technologies Institute  |  Microsoft Translator  |  Translators Without Borders


Homepage Story Archives