Faculty of Humanities & Sciences

This study investigated the psychometric properties of the Japanese version of the WHOQOL-BREF among 10,693 community-based married Japanese men and women (4376 couples) who were either expecting or raising a child. Analyses of item-response distributions, internal consistency, criterion validity, and discriminant validity indicated that the scale had acceptable reliability and performed well in preliminary tests of validity. Furthermore, dyadic confirmatory factor analysis revealed that the theoretical factor structure was valid and similar across partners, suggesting that men and women define and value quality of life in a similar way.

This paper describes an approach to processing meaning instead of processing information in computing. Human intellectual activity is supported by linguistic activities in the brain. Therefore, processing the meaning of language instead of processing information should be able to lead us to realize human intelligence on a computer. As an example of proposed framework for processing meaning, we build a travel consultation dialogue system which can understand utterance by a user and retrieve information through dialogue. Through a simulation example of the system, we show that both information processing and language processing are integrated into one processing.

The a Everyday language computing (ELC) is a new computational paradigm that all people, from small children to aged persons, can access and use computing systems with his/her own everyday language. As a way to realize ELC, we proposed a framework of language-based operating system (LOS), and we are now working intensively to develop the fundamental part of it. In this paper, we report our status of research on LOS. One of the main components of LOS is the semiotic base, which is a database of linguistic knowledge based on Systemic Functional Linguistic Theory. We explain the architecture of the semiotic base and corpus experiments conducted to determine the contents of it. A client's secretary agent is a user interface of LOS which realizes everyday language communication between a user and the system. We explain a client model that realizes personalized communication and the plan module that manages the structure of dialogue. In LOS, all kinds of information processing are done through everyday language. Language protocol is a computer protocol based on everyday language, and language-based application is a kind of agent software that provides services through language. We explain the characteristics of language protocol, the structure of language-based application programming interface (LAPI), and text interpretation process of language-based applications. Finally, we discuss prospects of this project and mention future work that remains to be done. We argue that by processing meaning of language rather than processing numbers, we attempt to provide a more human-like computer system and an intelligent computational environment to all people.

The objective of this paper is to show the text processing, especially text generation using the contextual features. For a computer system to operate everyday language the context which surrounds language use must be considered and this is one of the reasons why we adopt Systemic Functional Linguistics. In this paper we introduce the database for text processing system called "the Semiotic Base", which contains "the Context Base" as the model of the context and show how this system works in the text processing, especially in the text planning and generation.

It is natural to think that couples who work at a company or a person who lives by her/himself want to cook food for themselves as quickly and easily as possible when they are busy. However, to keep having the same food they can easily cook fed them up, therefore, it should be preferable for them to be recommended a variety of food that they can cook easily. Currently, there are so many Web sites for cooking recipes, and there are also recipes regarded as easy to cook on the sites. However, those recipes are not estimated as easy by taking user's conditions into account. The meaning of the word, "easy", would be differently interpreted by each user's conditions. Therefore, in this study, we aim to propose a method to recommend "easy" cooking recipes by considering user's conditions and then develop a recommendation system with the proposed method. Concretely, we collect approximately 10,000 recipes from AJINOMOTO Web recipe site; analyze the kinds of seasonings, ingredients, and cooking methods; and then make a ranking data set which expresses the difficulty for cooking. We develop a system that recommends "easy" cooking recipes based on the recommendation knowledge made by considering user's conditions.

In this paper, we propose a method to raise the accuracy of text classification based on latent topics, reconsidering the techniques necessary for good classification-for example, to decide important sentences in a document, the sentences with important words are usually regarded as important sentences. In this case, tf.idf is often used to decide important words. On the other hand, we apply the PageRank algorithm to rank important words in each document. Furthermore, before clustering documents, we refine the target documents by representing them as a collection of important sentences in each document. We then classify the documents based on latent information in the documents. As a clustering method, we employ the k-means algorithm and investigate how our proposed method works for good clustering. We conduct experiments with Reuters-21578 corpus under various conditions of important sentence extraction, using latent and surface information for clustering, and have confirmed that our proposed method provides better result among various conditions for clustering.

In a multi-class document categorization using graph-based semi-supervised learning (GBSSL), it is essential to construct a proper graph expressing the relation among nodes and to use a reasonable categorization algorithm. Furthermore, it is also important to provide high-quality correct data as training data. In this context, we propose a method to construct a similarity graph by employing both surface information and latent information to express similarity between nodes and a method to select high-quality training data for GBSSL by means of the PageRank algorithm. Experimenting on Reuters-21578 corpus, we have confirmed that our proposed methods work well for raising the accuracy of a multi-class document categorization.

Humans divide perceived continuous information into segments to facilitate recognition. For example, humans can segment speech waves into recognizable morphemes. Analogously, continuous motions are segmented into recognizable unit actions. People can divide continuous information into segments without using explicit segment points. This capacity for unsupervised segmentation is also useful for robots, because it enables them to flexibly learn languages, gestures, and actions. In this paper, we propose a Gaussian process-hidden semi-Markov model (GP-HSMM) that can divide continuous time series data into segments in an unsupervised manner. Our proposed method consists of a generative model based on the hidden semi-Markov model (HSMM), the emission distributions of which are Gaussian processes (GPs). Continuous time series data is generated by connecting segments generated by the GP. Segmentation can be achieved by using forward filtering-backward sampling to estimate the model's p...