Yoshio Nakao

An algorithm for one-page summarization of a long text based on thematic hierarchy detection

This paper presents an algorithm for text summarization using the thematic hierarchy of a text. The algorithm is intended to generate a one-page summary for the user, thereby enabling the user to skim large volumes of an electronic book on a computer display. The algorithm first detects the thematic hierarchy of a source text with lexical cohesion measured by term repetitions. Then, it identifies boundary sentences at which a topic of appropriate grading probably starts. Finally, it generates a structured summary indicating the outline of the thematic hierarchy. This paper mainly describes and evaluates the part for boundary sentence identification in the algorithm, and then briefly discusses the readability of one-page summaries.

Predicting types of protein-protein interactions using a multiple-instance learning model

We propose a method for predicting types of protein-protein interactions using a multiple-instance learning (MIL) model. Given an interaction type to be predicted, the MIL model was trained using interaction data collected from biological pathways, where positive bags were constructed from interactions between protein complexes of that type, and negative bags from those of other types. In an experiment using the KEGG pathways and the Gene Ontology, the method successfully predicted an interaction type (phosphorylation) to an accuracy rate of 86.1%.