Shino Iwashita

A model of rhetorical structure analysis of Japanese instructional texts and its application to a smart help system

The purpose of this paper is to propose an algorithm of rhetorical structure analysis of Japanese texts with special reference to wordprocessor help texts, which is to be realized in an interactive help system. The model of the rhetorical structure analysis presented in this paper is applicable to 25 texts (118 sentences) extracted from in the help texts accompanying Microsoft Word 2000. Also, several ways of utilizing the rhetorical structure of the help texts in information retrieval and text planning in the course of interaction with the user are proposed, so that it is possible to bring the computer closer to the people and make effective use of the existing resources.

Everyday language help system based on software manual

This paper presents a method for providing an everyday language smart help using an application software manual. This system takes three phases in the process: understanding of a users input, matching the result of understanding with manual texts of application software, and paraphrasing the matched texts to output for the user. We focus on the output phase, in which a manual text matched in the matching phase is paraphrased using the analysis result in the understanding phase. Four paraphrasing methods for a novice user are identified by a subject experiment, and rules for these methods are applied in respect to the linguistic features extracted in the understanding phase. An example scenario is shown, and the applied rules and their effects are discussed.

Script generation using rhetorical information in a task specification text

In order to extend the application domain of natural language interfaces to more realistic tasks without the decrease of users performance, it is desirable for users to be able to specify their requests as coherent texts consisting of more than one sentence. This paper presents a processing model of a natural language interface that accepts such an input text. Rhetorical information in an input text is used to generate a control structure of an output script program. Detection of loop structures, paraphrasing and dialogue are also incorporated. The algorithms explained in this paper have been implemented and evaluated in a personal email management domain.

Personalization of help system output in the framework of everyday language computing

This paper discusses providing the personalized output of a help system when a user has difficulties in operating computer software. The knowledge for personalization is stored in a client model, which is one of the modules in a client secretary in the framework of Everyday Language Computing. Three functions of the client model, i.e., paraphrasing, supplementing and omission, and inference, are performed to modify the existing help text so that it will be easily understood to users. Focusing on user’s knowledge, we have constructed a user’s knowledge level judging system. Finally, the importance of the personalization of the help output is discussed with an example dialogue.

Addition of facial expressions to facial caricature drawn using linguistic expressions

The paper aims at drawing an expressive facial caricature by adding facial expressions to an expressionless facial caricature that is drawn using linguistic expressions. The expressive facial caricature drawing procedure has two parts; the expressionless facial caricature drawing part and the facial expressions adding part. The former part has already been completed. In the paper the latter part is described. Facial expressions are added to the expressionless facial caricature using the relationship between the parameter value and facial expression that is obtained by the analysis of the questionnaire data.

Towards Programming in Everyday Language: A Case for Email Management

In order to extend the application domain of natural language interfaces to more realistic tasks without the decrease of user’s performance, it is desirable for users to be able to specify their requests as coherent texts consisting of more than one sentence, in other words, to write a program in everyday language. In this paper, we present a processing model of a natural language interface that accepts such an input text. It consists of the text understanding process using a systemic functional linguistic resource called the Semiotic Base, and the mapping process from the structure of the input text to the structure of an output computer program. The algorithms explained in this paper have been fully implemented in our everyday language programming system that deals with personal email management tasks.

Research report on Tangible Software Education

This paper describes an educational scheme involving “learning by producing in interesting software education” and “learning by experiencing in practical software education”. Outcomes are presented in the form of useful research activities and the educational scheme is discussed within the framework of the Tangible Software Engineering Education Project. The outcomes developed in the Project are introduced and their educational effectiveness is discussed.

A model of rhetorical structure analysis of Japanese texts and its application to intelligent text processing: a case for a smart help system

The purpose of this paper is to propose an algorithm of rhetorical structure analysis of Japanese instructional texts with special reference to wordprocessor help texts and ways of utilizing the rhetorical structure of the help texts in the course of providing the response to the user so that we can bring the computer closer to the people and make effective use of the existing resources.

A Study on Using Natural Language as a Computer Communication Protocol

This paper proposes a new computer communication protocol based on natural language called ‘language protocol’, a new communication method based on the protocol, and an interface, called ‘LAPI (Language Application Programming Interface)’, which can connect any communicaiton standard via natural language as a medium of the standards. With the proposed methods, we show the possibility of providing flexible communication environment for any communication object which achieves communication barrier-free in which all communication objects can communicate with natural language, and propose a new concept of ‘meaning processing’ against information processing of the conventional computing. An overview of language protocol communication environment is illustrated in Fig. 1.

Facial caricature drawing based on subjective impressions

In conventional studies of facial caricature drawing, image processing of a face picture is performed, and feature points are extracted. A caricature is drawn based on these points. On the other hand, there have been few studies of facial caricature drawing based on impressions, which are subjective and dependent on the person who views the face. The purpose of this paper is to draw a facial caricature using linguistic expressions in order to reflect personal impressions of a face. Cheerfulness, gentleness, and so on are considered as impressions of a face. The drawn facial caricature can be modified by the use of linguistic terms. The concept of exaggeration, which is important for emphasis of personality in a caricature drawing, is also introduced by considering the line thickness and the exaggeration rate. Facial caricatures are evaluated by subjects who themselves draw them by the presented method, and also by other subjects, and the validity of the process is discussed.© 2001 Scripta Technica, Syst Comp Jpn, 32(10): 1–12, 2001