• Annual Conference on Human and Language Technology
• /
• 1997.10a
• /
• pp.463-468
• /
• 1997

자연언어 대화는 사람들이 사용하는 가장 자연스러운 의사소통 수단이다. 따라서, 자연언어 대화 인터페이스를 통해서 사용자와 시스템이 편리하고 자연스러운 방법으로 의사를 교환할 수 있다. 본 논문에서는 대화 인터페이스의 필요성과 폼에 기반한 대화 인터페이스 기법에 대해서 설명한다, 폼 기반 인터페이스란 데이터베이스 검색을 위해서 질의어를 생성할 때 검색에 대한 제한 조건을 폼(form)의 형태로 나타내어, 사용자와의 대화를 통해서 폼 정보를 추출하고, 이렇게 완성된 폼을 이용하여 질의어를 생성하는 것을 말한다. 본 논문에서는 이러한 폼 기반 대화 인터페이스에서 시스템이 대화를 적절히 유도하고 사용자의 응답이나 질문에 대해 적절히 대응하기 위한 폼과 재귀적 대화 전이망(recursive dialogue transition networks)을 이용한 대화 모델에 대해 제안한다.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.135-139
• /
• 2009

In this paper we present INCUI, a user interface based on natural view of physical user interface of target devices and services in pervasive computing environment. We present a concept of Intuitively Natural and Consistent User Interface (INCUI) consisted of an image of physical user interface and a description XML file. Then we elaborate how INCUI template can be used to consistently map user interface components structurally and visually. We describe the process of INCUI mapping and a novel mapping method selection architecture based on domain size, types of source and target INCUI. Especially we developed and applied an extended LCS-based algorithm using prefix/postfix/synonym for similarity calculation.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06a
• /
• pp.221-224
• /
• 2011

관계에 대한 다양한 자연어 표현을 다루는 것은 구조 정보에 대한 자연어 질의 인터페이스 연구의 중요한 문제 중에 하나이다. 이러한 문제를 해결하기 위한 기존의 연구들은 자연어 질의 인터페이스를 대상 분야에 적합하게 구축하기 위한 수작업에 의존하였다. 이러한 접근은 소규모 구조 정보에 대한 자연어 질의 인터페이스 구축 시 효율적으로 적용될 수 있다. 하지만 최근에는 RDF와 OWL과 같은 그래프 구조 정보가 다양한 분야에서 대량으로 생성되고 있다. 수작업에 의존하는 접근을 통해 이러한 대량의 그래프 구조 정보에 대한 자연어 인터페이스를 구축하기에는 어려움이 있다. 본 논문은 자연어 인터페이스에 대한 자연어 표현의 다양성 문제를 해결하기 위해 자동으로 관계에 대한 자연어 표현을 수집하는 방법을 제안한다. 그래프 구조 정보에서 관계는 두 객체를 연결하는 유일한 에지(edge)로 표현된다. 제안한 방법은 주어진 에지로 연결되는 서로 다른 객체 쌍을 말뭉치(corpus)에서 검색하고 검색된 객체 쌍 주변에서 빈번하게 등장하는 자연어 표현을 수집한다. 자동으로 수집한 자연어 질의 표현을 자연어 인터페이스에 적용한 결과 수작업에 의존하는 기존 연구들과 비교할 만한 실험 결과를 보였다.

• The Journal of the Korea Contents Association
• /
• v.13 no.1
• /
• pp.55-63
• /
• 2013

NUI(Natural User Interfaces) has been developed through CLI(Command Line Interfaces) and GUI(Graphical User Interfaces). NUI uses many different input modalities, including multi-touch, motion tracking, voice and stylus. In order to adopt NUI to legacy GUI applications, he/she must add device libraries, modify relevant source code and debug it. In this paper, we propose a gesture-based interface model that can be applied without modification of the existing event-based GUI applications and also present the XML schema for the specification of the model proposed. This paper shows a method of using the proposed model through a prototype.

• (The)Korea Educational Review
• /
• v.23 no.1
• /
• pp.35-56
• /
• 2017

This study is to examine the effects of gesture based interface and display methods to make an effective virtual learning environment. The gesture based interface can provide interactive interface to make objects in the virtual learning environment by generating natural movement of users' gesture. This natural functionality leads users to apply natural movements as they do in real actions. Because of the natural user interface, the gesture based interface is expected to maximize learning outcomes. This study examined how the gesture based interface can be used when a head mounted display is applied for a virtual reality learning environment. For this study 44 colleagues students were participated. Two display methods (head mounted display vs. monitor) and two interface (gesture based interface vs. joystick) were tested to identify which might be more effective. The study was applied to different learning tasks which require different levels of spatial perception. The dependent variables are three constructs of virtual presence (spatial perception, immersiveness, and realness) and task completion time and recall tests. This study discussed potential disadvantages of gesture based interface while it showed positive usages of gesture based interface.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.6
• /
• pp.839-849
• /
• 2017

Recently, the role of the kitchen has evolved from the space for previous survival to the space that shows the present life and culture. Along with these changes, the use of IoT technology is spreading. As a result, the development and diffusion of new smart devices in the kitchen is being achieved. The user experience for using these smart devices is also becoming important. For a natural interaction between a user and a computer, better interactions can be expected based on context awareness. This paper examines the Natural User Interface (NUI) that does not touch the device based on the user interface (UI) of the smart device used in the kitchen. In this method, we use the image processing technology to recognize the user's hand gesture using the camera attached to the device and apply the recognized hand shape to the interface. The gestures used in this study are proposed to gesture according to the user's context and situation, and 5 kinds of gestures are classified and used in the interface.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.281-284
• /
• 2019

본 논문에서는 최근 인공지능 기반의 자연어이해기술을 활용한 자연어 인터페이스 표준화 현황을 소개하고 사물기반의 미디어 사물간의 기능들을 표준화하고 있는 MPEG IoMT 표준에서의 자연어 인터페이스 구현 내용을 소개한다. 자연어 인터페이스에는 음성인식 기술, 음성합성 기술, 언어처리 기술, 질의응답기술, 음성 자동통역 기술등이 포함되며 언어지능으로서의 자연어 인터페이스를 사물 인터넷 환경에서 구현하기 위해 MPEG IoMT 의 표준화된 포맷과 활용 방식을 소개한다.

• Korean Journal of Cognitive Science
• /
• v.3 no.2
• /
• pp.291-309
• /
• 1992

The computer manipulation by means of natural language prcessing will be not only helpful to use the computer with more simple and more comfortable but also flexiable to communicate between human and computers.In this paper the natural language interfaces will be applied to an intelligent geography tutoring systems(IGTS),and we will inspect the something to consider in the case of its implementation.Each module of IGTS is connected to the interface module and correspondence with each other for the sake of natural conversation between system and learner.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.2
• /
• pp.144-156
• /
• 2010

With the wide spread of Web services in various fields, there is a growing interest in building a composite Web service, however, it is very difficult for ordinary users to specify how to compose services. Therefore, a convenient interface for generating and invoking composite Web services are required. This paper proposes a natural language interface to invoke services. The proposed interface provides a way to describe users' requests for composite Web Services in a natural language. A user with no technical knowledge about Web services can describe requests for composite Web services through the proposed interface. The proposed method extracts a complex workflow and finds appropriate Web services from the requests. Experimental results show that the proposed method extracts a sophisticated workflow from complex sentences with many phrases and control constructs.

• Design Convergence Study
• /
• v.16 no.5
• /
• pp.177-190
• /
• 2017

This research aims to suggest a multimodal non-touch gesture interface design to improve the usability of 3D sculpting task. The task and procedure of design sculpting of users were analyzed across multiple circumstances from the physical sculpting to computer software. The optimal body posture, design process, work environment, gesture-task relationship, the combination of natural hand gesture and arm movement of designers were defined. The preliminary non-touch 3D S/W were also observed and natural gesture interaction, visual metaphor of UI and affordance for behavior guide were also designed. The prototype of gesture based 3D sculpting system were developed for validation of intuitiveness and learnability in comparison to the current S/W. The suggested gestures were proved with higher performance as a result in terms of understandability, memorability and error rate. Result of the research showed that the gesture interface design for productivity system should reflect the natural experience of users in previous work domain and provide appropriate visual - behavioral metaphor.