Robotic Receptionist
Meet Hala,the"roboceptionist," a computerized receptionist that is bilingual and sensitive to cultural nuance.
Developed by researchers at the University of Arizona (UA) and Carnegie Mellon University, the robot—named "Hala"—speaks both Arabic and English, and can tailor conversation to a person's cultural background.
At Carnegie Mellon's campus in Qatar, an existing version of the roboceptionist already greets visitors in the two languages. But because the machine is not sensitive to cultural cues, miscommunications often occur. For example, a user might request a meeting "week after week," which in English means "every week," but in some Arabic dialects means, "every other week." Sandiway Fong, a UA associate professor of linguistics and computer science, is now joining the team to fix cultural glitches like these.
"They invited me to join the team because they saw opportunities to generalize and improve the limited language capabilities of Hala," Fong said in a statement. "They needed Hala to be more flexible in dealing with language input from users. And that is where the University of Arizona comes in. We will provide both the language-specific and inter-language-related cultural capabilities so that this robot can be not just bilingual, but bicultural.
"You may speak Arabic, but you may choose to converse with the robot in English," said Fong. "You may be conversing with the sensibility and the cultural background and the idioms from the Arabic world. This robot needs to understand both."
Culture can dictate all aspects of communication, from syntax and sentence structure to greetings and politeness. A robot untrained in these aspects could confuse—or worse, offend—a user.
"In American culture, we quickly greet someone and then we tend to get down to business," explained Fong. "In Arab cultures, it is rude to actually get down to business right away. There is much more turn-taking in greetings. Hala will know this."
To make the robot more personable, the scientists have equipped it with a back story and personality. The computerized face is programmed with different expressions and can turn side-to-side. It's trained to determine questions such as "Is this person high-status?" and "Is this person in a hurry?"
Traditional computer translation programs are usually guided by parsed sentences from sources like the news. News stories, however, lack cultural styles such as questions, greetings and dialogue. The new Hala robot will be trained using data from transcripts of television interviews, which contain the necessary cultural cues.
"I'm very excited to be part of the project because I think that in developing these sorts of programs and in working with these sorts of robots, we eventually learn more about how we as humans function, how we learn and how we interact on a communicative level," said Samantha Wray, an incoming linguistics graduate student brought onto the project because of her experience with Arabic.
Beyond the "roboceptionist," the team's research could lead to computer help-agents, multicultural information kiosks, tour guides and automated international call centers.
"We foresee a future in which robots will help bridge gaps between people of different cultures," Fong said, "acting as intermediaries, to enable them to communicate more naturally and effectively."
Developed by researchers at the University of Arizona (UA) and Carnegie Mellon University, the robot—named "Hala"—speaks both Arabic and English, and can tailor conversation to a person's cultural background.
At Carnegie Mellon's campus in Qatar, an existing version of the roboceptionist already greets visitors in the two languages. But because the machine is not sensitive to cultural cues, miscommunications often occur. For example, a user might request a meeting "week after week," which in English means "every week," but in some Arabic dialects means, "every other week." Sandiway Fong, a UA associate professor of linguistics and computer science, is now joining the team to fix cultural glitches like these.
"They invited me to join the team because they saw opportunities to generalize and improve the limited language capabilities of Hala," Fong said in a statement. "They needed Hala to be more flexible in dealing with language input from users. And that is where the University of Arizona comes in. We will provide both the language-specific and inter-language-related cultural capabilities so that this robot can be not just bilingual, but bicultural.
"You may speak Arabic, but you may choose to converse with the robot in English," said Fong. "You may be conversing with the sensibility and the cultural background and the idioms from the Arabic world. This robot needs to understand both."
Culture can dictate all aspects of communication, from syntax and sentence structure to greetings and politeness. A robot untrained in these aspects could confuse—or worse, offend—a user.
"In American culture, we quickly greet someone and then we tend to get down to business," explained Fong. "In Arab cultures, it is rude to actually get down to business right away. There is much more turn-taking in greetings. Hala will know this."
To make the robot more personable, the scientists have equipped it with a back story and personality. The computerized face is programmed with different expressions and can turn side-to-side. It's trained to determine questions such as "Is this person high-status?" and "Is this person in a hurry?"
Traditional computer translation programs are usually guided by parsed sentences from sources like the news. News stories, however, lack cultural styles such as questions, greetings and dialogue. The new Hala robot will be trained using data from transcripts of television interviews, which contain the necessary cultural cues.
"I'm very excited to be part of the project because I think that in developing these sorts of programs and in working with these sorts of robots, we eventually learn more about how we as humans function, how we learn and how we interact on a communicative level," said Samantha Wray, an incoming linguistics graduate student brought onto the project because of her experience with Arabic.
Beyond the "roboceptionist," the team's research could lead to computer help-agents, multicultural information kiosks, tour guides and automated international call centers.
"We foresee a future in which robots will help bridge gaps between people of different cultures," Fong said, "acting as intermediaries, to enable them to communicate more naturally and effectively."
Comments