Tomoko Kojiri

The objective of our research is to develop a support system for creating presentation speech, especially speech that explains relations between two slides (complementary speech). Complementary speech is required between slides whose relations are difficult to understand from their contents, such as texts, figures, and tables. If authors could notice relations between created slides that are recognized by audiences, they would prepare appropriate complementary speech at the right places. To make authors notice slides where compl ementary speech is needed, our system analyzes relations between slides based on their texts and visualizes them. Four slide relations are defined and the method for detecting these relations from the slide texts is proposed. Then, analyzed relations are arranged in two-dimensional spaces that represent sequential relation and inclusive relation of their topics. The experimental results showed that most detected slide relations were the same as what examinees understood, and visualization of slide relations was useful in creating complementary speech.

When we translate Japanese sentence into English, sometimes several English words become the candidates. However, the usage situation of these candidate words is not the same. In order to choose appropriate words from them, we need to understand the usage situation for each candidate words. Usage situation of the words can be inferred by co-existing words in their example sentences. Co-existing words in example sentences are not always the same, so in order to understand usage situation, we need to generalize co-existing words from several example sentences. However, some of us who do not consciously generalize the co-existing words do not acquire the usage situation. This paper proposes the system which provides the environment where we can explicitly generalize co-existing words (keywords) in the example sentences to acquire the usage situation of the target words. This system also has a generalization support mechanism to provide concepts of words acquired through WordNet as hints. According to the experimental results, participants who used the system in learning English words reduced the number of incorrectly choosing the words and promoted to derive the own understanding of the usage situation.

Japan's largest platform for academic e-journals: J-STAGE is a full text database for reviewed academic papers published by Japanese societies

A research presentation integrates slides and speech. If these two aspects do not represent the same intention, the presentation will probably fail to effectively explain the presenter’s intention. This paper focuses on the representation of the critical contents in a presentation. In an effective speech, the speaker adds more intonation and stress to emphasize the importance of the slide contents. Audiences recognize that important contents are those that are explained in a stronger voice or that are said after a short pause. However, in ineffective speeches, such voice effects do not always correspond to the important contents that are indicated by slides. On slides, the important contents are represented by levels of text indentation and size, color, and animation. This research develops a presentation speech support system that estimates important contents from slides and voices that might be recognized by audiences and extracts numerical differences. In addition, the system provides comments and feedback to improve speeches.

Historical events include lessons of good and bad behaviors of human beings. To discover these lessons, we must generalize the historical event by the basic attributes, so that we can notice the underlying patterns that commonly occur in multiple historical events. Based on this viewpoint, we have developed a learning system that supports the generalization of historical events based on the basic attributes and helps finding lessons by comparing common patterns from two generalized events. In this paper, the effect of our system is discussed based on the experimental result.