Ayako Hoshino

Learn More
An automatic generation of multiplechoice questions is one of the promising examples of educational applications of NLP techniques. A machine learning approach seems to be useful for this purpose because some of the processes can be done by classification. Using basic machine learning algorithms as Naive Bayes and K-Nearest Neighbors, we have developed a(More)
Creating good proposals is critical to the success of many organizations. In spite of this, proposal generation is typically ad hoc, often inefficient and relies heavily on wisdom, skills and resources that participants accumulate informally over time. We studied the tactics that informants believed were helpful and how past content and successful(More)
New strongylophorines-22 (1), -23 (2), -24 (3), and -25 (4) were isolated from the Okinawan sponge Petrosia (Strongylophora) corticata along with other known strongylophorines. The structures of these strongylophorines were determined on the basis of spectroscopic analysis and chemical conversions. Assessment was also made of the cytotoxicity of(More)
In real-world dirty data, errors are often not randomly distributed. Rather, they tend to occur only under certain conditions, such as when the transaction is handled by a certain operator, or the weather is rainy. Leveraging such common conditions, or “cause conditions”, the proposed data-cleansing algorithm resolves multi-tuple conflicts with high speed,(More)
This study describes a statistically motivated approach to constraint-based data cleansing that derives the cause of errors from a distribution of conflicting tuples. In real-world dirty data, errors are often not randomly distributed. Rather, they often occur only under certain conditions, such as when the transaction is handled by a certain operator, or(More)