Mikio Nakano

Learn More
This paper concerns the discourse understanding process in spoken dialogue systems. This process enables the system to understand user utterances based on the context of a dialogue. Since multiple candidates for the understanding result can be obtained for a user utterance due to the ambiguity of speech understanding, it is not appropriate to decide on a(More)
This paper proposes a probabilistic approach to the resolution of referring expressions for task-oriented dialogue systems. The approach resolves descriptions, anaphora, and deixis in a unified manner. In this approach, the notion of reference domains serves an important role to handle context-dependent attributes of entities and references to sets. The(More)
This paper proposes a method for incrementally understanding user utterances whose semantic boundaries are not known and responding in real time even before boundaries are determined. It is an integrated parsing and discourse processing method that updates the partial result of understanding word by word, enabling responses based on the partial result. This(More)
We developed a multi-domain spoken dialogue system that can handle user requests across multiple domains. Such systems need to satisfy two requirements: extensibility and robustness against speech recognition errors. Extensibility is required to allow for the modification and addition of domains independent of other domains. Robustness against speech(More)
When designing a spoken dialogue system, in particular a real-time one, not only what the system responds but also when it responds need to be considered. This paper focuses on when the system should appropriately respond with backchannels, and reports an experiment that compared two response-time conditions: the immediate response and the orderly response.(More)
This paper describes MOKUSEI, an end-to-end Japanese version of our JUPITER weather information system. MOKUSEI delivers weather information over the phone through natural conversation with the user. For the most part, MOKUSEI uses the same components for recognition, understanding, and generation that JUPITER uses, and the database and the semantic frames(More)
Animated agents that act and speak as attendants to guests on shopping web sites are becoming increasingly popular. Inspired by this development, we propose a new method of presentation using a humanoid robot. Humanoid presentations are effective in a real environment because they can move and look around at the audience similar to a human presenter. We(More)
Ideally, the users of spoken dialogue systems should be able to speak at their own tempo. The systems thus need to correctly interpret utterances from various users, even when these utterances contain disfluency. In response to this issue, we propose an approach based on a posteriori restoration for incorrectly segmented utterances. A crucial part of this(More)