Computer Assistance in Bilingual Task-Oriented Human-Human Dialogues

Sven Schmeier; Matthias Rebel; Renlong Ai

In: Proceedings of the 14th International Conference on Human-Computer Interaction. Human Computer Interaction International Conferences (HCII-2011), July 9-14, Orlando, Florida, USA, Springer, 2011.


In 2008, the percentage of people with a migration background in Germany had already reached more than 15% (12 Million people). Among that 15%, the ratio of seniors aged 50 years or older was 30% [1]. In most cases, their competence of the German language is adequate for dealing with everyday situations. However sometimes in emergency or medical situations, their knowledge of German is not sufficient to communicate with medical professionals and vice versa. These seniors are part of the main target group within the German Ministry of Research and Education (BMBF) research project SmartSenior [2] and we have developed a software system that assists multilingual doctor-patient conversations to overcome language and cultural barriers. The main requirements of such a system are robustness, accurate translations in respect to context and mobility, adaptability to new languages and topics and of course an appropriate user interface. Furthermore, we have equipped the system with additional information to convey cultural facts about different countries. In this paper, we present the architecture and ideas behind the system as a whole as well as related work in the area of computer aided translation and a first evaluation of the system.


final_hci.pdf (pdf, 494 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence