In this paper, we propose the method to estimate the meaning of an alphabetical abbreviation. To resolve the polysemy of alphabetical abbreviations, this method uses the concept base, Wikipedia, and, the evaluation approach for semasiological association between sentences. The concept base allows Conceptualization of a word. We apply Calculation of Degree of Association or Earth Mover's Distance (EMD) to evaluate semasiological association between sentences. This paper used 129 articles to evaluate the proposal method. 129 articles included 129 meanings of alphabetical abbreviations and 58 literation of alphabetical abbreviations. The experiments showed that the accuracy of the proposal method was close to 80%.
Recently, increasing digital music collections make us difficult to find new favorite music which we are really interested in. To overcome this problem, content-based music information retrieval has been studied. It enables users to search similar music with users choose, however few method can improve search result interactively. In this paper, we propose a new method that allows users to reflect their search intention. By selecting SNS tags, users can naturally inform their intention to a music retrieval system, and the system utilize user feedback to modify a similarity function. we employ learning to rank technique to utilize tag information to modify a feature vector space.
And the knowledge of one field based on, in order to analogize the knowledge of other fields, it is necessary to understand the nature to be a common point of both the knowledge . Even if only the formula is remembered earnestly , and there is a formula of the same meaning of the plural by solved learning method without also understanding kind in learning of mathematics , it'll be the circumstances which can't be applied because those are remembered as the separate formula . In this study , problem of different fields with a common essence , we propose a learning system to support the analogy of both fields on an understanding of the essence .
These days,in the education field,in order to foster a solid academic achievement, there is a need to enhance the learning motivation of the children. In this study, We propose the framework that was added to the Functions that can be viewed the Story depending on certain learning outcomes, and Life Function that give a constraint on the number of times that can be addressed to exercise in the typical learning system, as an element to promote the elevation and maintenance of learning motivation.
The total environment for text data mining, includes a number of mining tools, which allows the text analysis in a variety of ways. When performing text mining, it is necessary to analyze the results of the analysis widely collected. However, it is limited in the idea of one person. If it is possible to see how to use the unknown tools, it may be connected to the idea of obtaining new results. Therefore, this study suggests function for TETDM user to share with each other the operation history of the tool.
Total environment for text data mining TETDM, also to people of non-specialists of text mining, is used to analyze the Web page, e-mail, SNS and BBS comments, as an environment that is used to analyze the text information is many opportunities to see it is.In addition, by the user to increase, increased development motivation of tool developers is considered an advantage to be easily added to the total environment occurs.So, with the aim of improve the motivation to use TETDM, we propose a game mode add the elements of the game.
In the process of convergence of knowledge creation in text mining, by repeating the interpretation and integration of the collected analysis result, we are aiming to acquire a straightforward knowledge represented as cause-and-effect relationship. In this study, by the "multi-stage of interpretation" that make giving a repeat interpretation in one of the results, provide assistance leading to the acquisition of general knowledge by extending the width of the interpretation. In addition, by the "cause and result of labeling" to the interpretation, provide assistance to integrate knowledge as a cause-and-effect relationship.
In this paper, we discuss automatic collection and visualization of the expressions that represent changes of situations in our society. In creating new products or making a new plan, it is necessary to grasp the change in social situation. There are various ways in which we may find changes of situation in our society. For some of them, such as statistical manners, we have to begin with discussion of how to interpret them. We focus on expression on Web documents that seem to be written as authors' own interpretation of chages of situations in our society. We propose a method to collect them automatically from the Web documents. We also discuss a visualization method to help users to understand the collected expressions easily.
A lack of the communication ability I met by the spread of an information terminal in the present society is being a problem. So the contents which are conversation using a head-mounted display of the see-through type when getting communication at the meeting by this research, and, the system to recommend and show the next topic in real time is proposed. Continuation of conversation with the partner who had no dialogue experience so much up to now is suggested by this.
Components of scholarly papers bear roles such as title, body, itemization title, or figure. A role label enables advanced searching such as finding papers in which a specified keyword is used in a specified role. In this paper, we propose a fully automatic role labeling method for OCR processed scholarly papers. In the proposed method, we first identify components from the OCR processed images by reconstructing components from incorrectly recognized regions by OCR software. Next, we assign role labels to the components. Our experiment showed that the accuracy of the classification reached 94% in the best case.