• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권5호
• /
• pp.1396-1412
• /
• 2023

Conversation modeling is an important and challenging task in the field of natural language processing because it is a key component promoting the development of automated humanmachine conversation. Most recent research concerning conversation modeling focuses only on the current utterance (considered as the current question) to generate a response, and thus fails to capture the conversation's logic from its beginning. Some studies concatenate the current question with previous conversation sentences and use it as input for response generation. Another approach is to use an encoder to store all previous utterances. Each time a new question is encountered, the encoder is updated and used to generate the response. Our approach in this paper differs from previous studies in that we explicitly separate the encoding of the question from the encoding of its context. This results in different encoding models for the question and the context, capturing the specificity of each. In this way, we have access to the entire context when generating the response. To this end, we propose a deep neural network-based model, called the Context Model, to encode previous utterances' information and combine it with the current question. This approach satisfies the need for context information while keeping the different roles of the current question and its context separate while generating a response. We investigate two approaches for representing the context: Long short-term memory and Convolutional neural network. Experiments show that our Context Model outperforms a baseline model on both ConvAI2 Dataset and a collected dataset of conversational English.

• 영어어문교육
• /
• 제16권4호
• /
• pp.267-290
• /
• 2010

The purpose of this study is to analyze the writing tasks included in the newly developed high school English textbooks in the aspects of genre, rhetorical structure, task type, and authenticity in order to find out whether these tasks could contribute to improving Korean EFL students' writing skills. A total of nine textbooks were selected for the study and every writing task in each textbook was analyzed. The results show that various types of genres were incorporated in the tasks, but very few opportunities were provided for students to acquire characteristics of specific genres. In terms of rhetorical structure of text, narration, illustration, and transaction were required most, whereas not a single writing task asked students to use classification or cause and effect. Many of the writing tasks analyzed offered linguistic and/or content support through the use of models, which displays traces of the product-based approach to teaching writing. Lastly, most of the tasks lacked authenticity represented by explicit discussion of purpose and audience. Implications for L2 writing task development and writing instruction in the Korean EFL context are discussed.

• 대한산업공학회지
• /
• 제41권4호
• /
• pp.389-395
• /
• 2015

According to much research on cognitive science, the impact of the scene-context on human visual search in real-world images could be as important as the saliency. Therefore, this study proposed a method of Adaptive Control of Thought-Rational (ACT-R) modeling of visual search in real-world images, based on saliency and scene-context. The modeling method was developed by using the utility system of ACT-R to describe influences of saliency and scene-context in real-world images. Then, the validation of the model was performed, by comparing the data of the model and eye-tracking data from experiments in simple task in which subjects search some targets in indoor bedroom images. Results show that model data was quite well fit with eye-tracking data. In conclusion, the method of modeling human visual search proposed in this study should be used, in order to provide an accurate model of human performance in visual search tasks in real-world images.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제8권12호
• /
• pp.499-506
• /
• 2019

지능형 로봇은 사용자의 요구에 따라 상황에 맞는 작업을 선택하여 서비스를 수행할 수 있어야 하며, 다양한 상황에 대해서 현재 가장 적합한 작업이 무엇인지 비교하고 선택할 수 있어야 한다. 이를 위해 절차적 추론 시스템을 활용하는 기존의 지능형 로봇시스템은 작업 모델 내부에 우선도 함수를 정의하고 이를 활용하여 작업 간 우선도를 비교하는 방법으로 작업관리 기능을 제공하고 있었다. 하지만 이러한 기존의 방법은 다중 도메인 서비스를 수행하는 데에 있어, 우선도 결정 함수가 명시적이지 않아 일반적인 상황에 대한 우선순위를 결정할 수 없고, 유용성을 비교하기 위한 표준적인 기준이 존재하지 않아 각 서비스 간의 우선도를 비교하는 방법이 범용적이지 않으며, 이를 재사용하거나 확장할 수 없다는 한계점이 존재했다. 우리는 이를 개선하기 위해 작업관리를 위한 정책 모델과 이를 활용하여 작업의 우선도를 계산하는 방법인 정책 모델 주도 메타-플래닝을 제안한다. 정책 모델은 메타-플래닝 과정에서 작업의 유틸리티를 명시적으로 계산할 수 있는 기능을 제공하며, 기초 모델을 통해 다양한 서비스 간의 유용성을 비교할 수 있게 해준다. 또한, 모델의 구성을 온톨로지를 활용함으로써 확장성을 가지는 특징이 있다. 실험을 통해 동적 환경에서 정책 모델에 따라 로봇의 행동이 변화하는 것을 관찰할 수 있었고, 이를 통해 서비스가 필요에 따라 우선도의 비교를 통해 선택되는 것을 확인할 수 있었다.

• Asia pacific journal of information systems
• /
• 제24권3호
• /
• pp.345-370
• /
• 2014

The notion of technological adoption such as Radio Frequency Identification (RFID) has been examined in various domains such as supply chain management, inventory management and health care. However, there are several unanswered questions surrounding how this technology is adopted in disaster management. This study attempts to explore the potential of RFID in disaster management. The notion of Task-Technology Fit (TTF) is deemed suitable for this purpose and thus used as the theoretical framework that is further validated by employing multiple case studies. The empirical findings indicate that there are six key factors influencing the decision to adopt RFID in disaster management. Some relate to aspects of RFID when it is put into practice, namely cost, compatibility, standardisation, implementation and locatability; while the other key factor relates to privacy and security aspect of information. It is hoped that the findings of this research will inform disaster management organizations to better plan the adoption of RFID for their operations.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2002년도 춘계학술발표논문집 (상)
• /
• pp.687-690
• /
• 2002

In this paper, we present a novel semaphore implementation scheme which shortens finish time of high priority tasks and improves reliability of a system. The real-time systems have time constraints. Especially, the task with hard real-time constraints must meet its deadline. Consequently, managing shared resources is considered guaranteeing mutual exclusion as well as meeting task's deadline under unfavorable condition. According to the number and sort of the locked semaphores under the event occurred, this paper presents the reduction of the finish time of high priority task by decision whether the context switched or not. The experimental results show that the proposed method gives performance improvements in finish time of high priority tasks of about 11% over zuberi[4] method.

• Journal of Information Technology Applications and Management
• /
• 제12권2호
• /
• pp.145-161
• /
• 2005

In this paper, we present an experiment conducted to examine how the web site's architecture, content quantity and the user task complexity affect its usability. The experiment was performed in two phases on college students to visit existing web sites which are readily accessible via the Internet. The results of experiment show that the web site's architecture significantly affects the efficiency and the effectiveness interactively with its content quantity and the user task's complexity. On the other hand, none of the above three factors show significant effects on the satisfaction and the learnability. In particular, the web site's content quantity does not have any statistically significant effects on the satisfaction and the learnability. It implies that the factors affecting the satisfaction and the learnability are different from those affecting the efficiency and the effectiveness. The analysis reassures that it is essential to consider the context of use in designing a web site.

• 한국멀티미디어학회논문지
• /
• 제10권6호
• /
• pp.799-806
• /
• 2007

The prototypical smart environment to support the context-aware interactions between user and ubiquitous campus environment based on multi-agent system paradigm is proposed in this paper. In this model, the dynamic Bayesian is investigated to solicit and organize agents to produce information and presentation assembly process in order to allocate the resources for an unseen task across multiple services in a dynamic environment. The user model is used to manage varying user constraints and user preferences to achieve system's goals.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2008년도 한국컴퓨터종합학술대회논문집 Vol.35 No.1 (D)
• /
• pp.352-355
• /
• 2008

네트워크 기반의 IP 이동성 지원에 대한 요구가 증대됨에 따라 IETF NetLMM(Internet Engineering Task Force Network-based Localized Mobility Management WG)에서는 Proxy MIPv6에 대한 표준화작업이 진행 중에 있다. 또한 지연시간에 민감한 실시간 서비스 (VoIP 등)를 지원하기 위해 보다 빠른 핸드오프를 위 한 다양한 기법이 제안되고 있다. 본 논문에서는 Context Transfer Protocol 개념을 적용하여 주요 지연시간이 발생되는 AAA 인증시간을 줄이고 다양한 모바일노드의 이동 시나리오를 고려하여 모바일노드의 이동성을 보장 및 지연시간을 최소화하는 기법을 제안한다.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.108-113
• /
• 2009

Significant attention has recently been drawn to digital home photo albums that use face detection technology. The tendency can be found in home photo albums that people prefer to allocate concerned objects in the center of the image rather than the boundary when they take a picture. To improve detection performance and speed that are important factors of face detection task, this paper proposes a face detection method that takes spatial context information into consideration. Experiments were performed to verify the usefulness of the proposed method and results indicate that the proposed face detection method can efficiently reduce the false positive rate as well as the runtime of face detection.