Language understanding is one of key technologies for designing an intelligent CW - natural language understanding and action control project

摘要

Summary form only given. The project Natural Language Understanding and Action Control started in 2001 as 5-year research project of a Grant-in-Aid for Creative Scientific Research supported by the Ministry of Education, Culture, Sports, Science and Technology, and Japan Society for the Promotion of Science. The research objectives are summarized as follows: to explore the relation between language understanding and actions; to build a human friendly machine interface; to develop a new interdisciplinary research area. During the period 2001-2004, many interesting research results have been obtained. Following are some main accomplishments: 1) basic research - analysis of spoken language, space understanding, and the relation between language and action from the point of linguistics, cognitive science, and cognitive linguistics, respectively; 2) spoken language understanding and dialogue management - resolution of anaphora and ellipsis, object identification, handling vagueness, discourse management, morphological analysis for spoken language, real time speech recognition, robust speech recognition in noisy environment, handling ill-formed expressions (e.g. fillers, repetitions and repair expressions), speech synthesis; 3) robotics and computer graphics -constructing a life-like 3-dimensional software agent capable of performing many actions in a vitual world, and a hardware service robot, sign language understanding, a robot capable of communicating with a human through non-verbal expressions (e.g. nodding and gazing); 4) prototype system development - animated agent system that understands spoken language commands and performs actions in a virtual space, a service robot to help a human, a guidance robot, sign language understanding system, hardware robot capable of performing non-verbal expressions. Note that the results obtained from our research on software agent should be naturally applicable to hardware robots. This progress report collects only the research results obtained in 2004. Progress reports period 2001-2003 are available by consulting URL address as shown [http://www.cl.cs.titech.ac.jp/sinpro/]. I have introduced this project more precisely as invited speech and consider why language understanding is one -of key technologies for designing an intelligent CW.