Kenji Matsumoto

Learn More
BACKGROUND Oxytocin is known to be related to social behaviors, including trust. However, few studies have investigated the association between oxytocin levels and social capital. Thus, we tested the hypothesis that endogenous oxytocin levels are positively associated with social capital. We also considered whether the association differed across gender(More)
One of the crucial parts of any corpus-based machine translation system is a large-scale bilingual corpus that is aligned at various levels such, as the sentence and phrase levels. This kind of corpus, however, is not easy to obtain, and accordingly, there is a great need for an efficient construction method. We approach this problem by integrating two(More)
We have attempted to use information theoretic quantities for analyzing neuronal connection structure from spike trains. Two point mu tual information and its maximum value, channel capacity, between a pair of neurons were found to be useful for sensitive detection of crosscorrelation and for estimation of synaptic strength, respectively. Three point mutual(More)
This paper describes ongoing research on a Japanese-to-English speech-to-speech translation system for " controlled monologue", such as TV news and commentary programs in which the speaking styles are controlled as a monologue. We have adopted the data-driven approach since the TV programs in question cover a wide range of topics, and because it seems much(More)
According to artificial intelligence studies, goal-based and utility-based agents can select an action to attain a desired outcome. The goal-based agent sets a specific goal regardless of its utility at first, and selects the action that leads to that goal (goal-based action selection). The utility-based agent compares the utilities of different possible(More)
The extraction of important sentences is a key technique for automatic summarization. Whereas most research in this area has targeted written language, we are conducting research on spoken language monologues such as presentations and TV news commentary programs. We collected 50 TV news commentary programs, and experimented with the extraction of important(More)
  • 1