Minoru Sasaki

Learn More
Spectral clustering is a powerful clustering method for document data set. However, spectral clustering needs to solve an eigenvalue problem of the matrix converted from the similarity matrix corresponding to the data set. Therefore, it is not practical to use spectral clustering for a large data set. To overcome this problem, we propose the method to(More)
In this paper, we improve an unsuper-vised learning method using the Expectation-Maximization (EM) algorithm proposed by Nigam et al. for text classification problems in order to apply it to word sense disambigua-tion (WSD) problems. The improved method stops the EM algorithm at the optimum iteration number. To estimate that number, we propose two methods.(More)
— When grasping an object, friction forces are sometimes utilized. Because of this friction forces, the object is manipulable to various direction. In this paper, we discuss which direction is best when contact points, the number of which is two in the 2D-space grasping or three in the 3D one, are assigned. To evaluate the object direction, we focus on the(More)
— When grasping an object, friction forces are sometimes utilized effectively. This friction forces allows us to manipulate the object to various directions. Regarding such a grasped object posture, we reported an analysis on the 2D-space grasping with two contact points. Selecting the square sum of the contact forces as an evaluation function of the object(More)
In this paper, we describe a system that divides example sentences (data set) into clusters, based on the meaning of the target word, using a semi-supervised clustering technique. In this task, the estimation of the cluster number (the number of the meaning) is critical. Our system primarily concentrates on this aspect. First, a user assigns the system an(More)
This paper proposes and method to improve retrieval performance of the vector space model (VSM) by utilizing user-supplied information of those documents that are relevant to the query in question. In addition to the user's relevance feedback information, incorporated into the retrieval model, which is built by using a sequence of linear transformations, is(More)