GlobalMind - Bridging the Gap Between Different Cultures and Languages with Common-sense Computing

The need for more effective communication across different countries has increased as the interactions between them have been growing. Communication is often difficult because of both language differences and cultural differences. Although there have been many attempts to meet the communication need on the level of language with machine translators and dictionaries, many problems related to cultural and conceptual differences still remain. To improve traditional machine translators and cross-cultural communication aids, it is necessary to develop automated mechanisms to analyze cultural differences and similarities. This thesis approaches the problems with automatic computation of cultural differences and similarities. This thesis, GlobalMind, provides common-sense databases of various countries and languages and two inference modules to analyze and compute the cultural differences and similarities from the databases. I describe the design of GlobalMind databases, the implementation of its inference modules, the results of an evaluation of GlobalMind, and available applications. Thesis Supervisor: Walter Bender Title: Senior Research Scientist, MIT Media Laboratory