• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.454-460
• /
• 2023

대규모 언어 모델(Large Language Models, LLM)의 발전과 더불어 대량의 학습 데이터로부터 기인한 LLM의 편향성에 관심이 집중하고 있다. 최근 선행 연구들에서는 LLM이 이러한 경향성을 탈피하고 다양한 언어 패턴을 생성하게 하기 위하여 LLM에 여러가지 페르소나를 부여하는 방법을 제안하고 있다. 일부에서는 사람의 성격을 설명하는 성격 5 요인 이론(Big 5)을 이용하여 LLM에 다양한 성격 특성을 가진 페르소나를 부여하는 방법을 제안하였고, 페르소나 간의 성격의 차이가 다양한 양상의 언어 사용 패턴을 이끌어낼 수 있음을 보였다. 그러나 제한된 횟수의 입력만으로 목표하는 성격의 페르소나를 생성하려 한 기존 연구들은 세밀히 서로 다른 성격을 가진 페르소나를 생성하는 데에 한계가 있었다. 본 연구에서는 페르소나 부여 과정에서 피드백을 반복하여 제공함으로써 세세한 성격의 차이를 가진 페르소나를 생성하는 방법론을 제안한다. 본 연구의 실험과 분석을 통해, 제안하는 방법론으로 형성된 성격 페르소나가 다양한 언어 패턴을 효과적으로 만들어 낼 수 있음을 확인했다.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.5
• /
• pp.586-590
• /
• 2010

In this paper we formally define the linear detrending subsequence matching and propose its efficient index-based solution. To this end, we first present the notion of LD-windows. We eliminate the linear trend from a subsequence rather than each window itself and obtain LD-windows by dividing the subsequence into windows. Using the LD-windows we present a lower bounding theorem of the index-based solution and formally prove its correctness. Based on this lower bounding theorem, we then propose the index building and subsequence matching algorithms, respectively. Finally, we show the superiority of our index- based solution through experiments.

• Economic and Environmental Geology
• /
• v.32 no.5
• /
• pp.537-544
• /
• 1999

In mineral exploration, there are many data sets which need to be created, processed and analyzed in order to discover a favorable mineralized zone. Recently, with Geographic Information System (GIS), such exploration data sets have been able to be systematically stored and effectively processed using computer technologies. In this study, most exploration data sets were first digitized and then rasterized. Furthermore, they were integrated together by using fuzzy set theory to provide a possibility map toward a target hypothesis. Our target hypothesis is "there is a skarn magnetite deposit in this study" and all fuzzy membership functions were made with respect to the target hypothesis. Test area is extended from 37:00N/l28:30E to 37:20N/I28:45E, approximately 20 km by 40 km. This area is a part of Taebaeksan mineralized areas, where the Sinyemi mine, a skarn magnetite deposit, is located. In final resultant map, high potential or possibility area coincides with the location of the Shinyemi mine. In this regard, we conclude the fuzzy set theory can be effectively applied to this study and provides an excellent example to define potential area for further mineral exploration.

• Journal of KIISE:Computer Systems and Theory
• /
• v.28 no.5
• /
• pp.213-217
• /
• 2001

Excessive memory buffer requirement in continuous media playback is a serious impediment of wide spread usage of on-line multimedia service. Skewed access frequency of available video files provides an opportunity of re-using the date blocks which has been loaded by one session for later usage. We present novel algorithm which minimizes the buffer requirement in multiple sessions of multimedia playbacks. In continuous media playback originated from the disk, a certain amount of memory buffer is required to synchronize asynchronous disk. Read operation and synchronous playback operation. As aggregate playback bandwodth increases, larger amount of buffer needs to be allocated for this synchronization purpose. The focus of this work is to study the asymptotic behavior of the synchronization buffer requirement and to develop an algorithm coping with this excessive buffer requirement under bandwidth congestioon. We argue that in a large scale continuous media server, it may not be necessary to read the blocks for each session directly from the disk. The beauty of our work lies in the fact that it dynamically adapts to disk utilization of the server and finds the optimal way of servicinh the individual sessions while minimizing the overall buffer space requirement. Optimality of the proposed algorithm is shown by proof. The effectiveness and performance of the proposed scheme is examined via simulation.

• Korean Journal of Cognitive Science
• /
• v.35 no.1
• /
• pp.23-48
• /
• 2024

Building human-aligned artificial intelligence (AI) for social support remains challenging despite the advancement of Large Language Models. We present a novel method, the Chain of Empathy (CoE) prompting, that utilizes insights from psychotherapy to induce LLMs to reason about human emotional states. This method is inspired by various psychotherapy approaches-Cognitive-Behavioral Therapy (CBT), Dialectical Behavior Therapy (DBT), Person-Centered Therapy (PCT), and Reality Therapy (RT)-each leading to different patterns of interpreting clients' mental states. LLMs without CoE reasoning generated predominantly exploratory responses. However, when LLMs used CoE reasoning, we found a more comprehensive range of empathic responses aligned with each psychotherapy model's different reasoning patterns. For empathic expression classification, the CBT-based CoE resulted in the most balanced classification of empathic expression labels and the text generation of empathic responses. However, regarding emotion reasoning, other approaches like DBT and PCT showed higher performance in emotion reaction classification. We further conducted qualitative analysis and alignment scoring of each prompt-generated output. The findings underscore the importance of understanding the emotional context and how it affects human-AI communication. Our research contributes to understanding how psychotherapy models can be incorporated into LLMs, facilitating the development of context-aware, safe, and empathically responsive AI.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.2
• /
• pp.343-348
• /
• 2020

During 50 years, the chaotic theory has begun to research with concerning in Mathematics and physics, and it has extended the fields to of engineering and social science. Recently, chaotic theory has progressed as a type of fusion research fused with natural science and social science. Such fused research includes problems for addiction, happiness of human, problem happened between family and love affairs between man and woman. In this paper, we consider the external environment based on love model which is one among fusion research, and when we consider colored noise in the external environment, we verify how the chaotic pattern is affected in the love model through time series and phase portrait.

• Journal of KIISE:Computer Systems and Theory
• /
• v.27 no.11
• /
• pp.881-889
• /
• 2000

프로그램의 실행시간은 캐쉬메모리의 효율적 사용과 밀접한 관계가 있다. 특히 간섭 실패는 프로그램의 성능에 큰 영향을 미치지만 나타나는 형태가 불규칙적이므로 예측하기가 매우 어렵다. 본 논문에서는 직접 사상 캐쉬전략을 사용한 완전 중첩 루프 내 배열의 캐쉬 실패율(cache miss ratio)을 구하는 분석적 모델을 제시한다. 논문에서 제시한 모델을 임의의 캐쉬 위치에 각 배열이 접근한 시간을 기반으로 다음주기에서 캐쉬 실패의 발생 여부를 예측하는데, 간섭으로 발생한 캐쉬 실패 개수에 대해 기존에 제시된 모델보다 더 빠르고 정확한 예측이 가능하다. 특히, 한문장의 수행시간 예측시간은 배열의 크기와 독립적이기 때문에, 전체 프로그램의 수행시간 예측은 배열의 크기 및 문장의 반복 회수 배만큼 빠른 결과를 보여준다. 본 모델은 프로그램의 성능예측 뿐만 아니라 데이터 지역성의 최적화, 캐쉬 구성, 스케쥴링 등에서도 이용 가능하다.

• Journal of KIISE:Databases
• /
• v.37 no.6
• /
• pp.285-291
• /
• 2010

In this paper, we propose a new paradigm of weighting methods for naive Bayesian learning. We propose more fine-grained weighting methods, called value weighting method, in the context of naive Bayesian learning. While the current weighting methods assign a weight to an attribute, we assign a weight to an attribute value. We develop new methods, using Kullback-Leibler function, for both value weighting and feature weighting in the context of naive Bayesian. The performance of the proposed methods has been compared with the attribute weighting method and general naive bayesian. The proposed method shows better performance in most of the cases.

• Journal of KIISE:Computer Systems and Theory
• /
• v.28 no.7
• /
• pp.317-330
• /
• 2001

대규모 가상환경의 핵심은 사용자 PC의 성능에 영향을 받는 확장성에 있다. 기존의 접근 방식은 대규모 환경을 지원하기 위해 멀티캐스트를 주로 사용하였다. 그러나 멀티캐스트는 현재 멀티캐스트 하드웨어가 지원할 수 있는 그룹의 수가 제한된다는 문제점이 있다. 본 논문에서는 PC 클라이언트와 인터넷과 같은 대규모 네트워크 기반의 확장성 높은 가상환경 모델을 제시한다. 멀티캐스트 네트워크와 PC 클라이언트 사이에 위치하는 관심영역 관리자(AOIM)는 멀티캐스트 그룹과 함께 다중 필터링을 수행하여 정보의 흐름을 최적화한다. 또한, 관심영역 관리자는 사용자의 관심 패턴에 따라 관심영역(AOI)으로부터 PC 클라이언트로의 데이터 전송량을 조절한다. 관심영역은 정보의 정확도에 따라 세 단계로 구분되며, 각 단계의 구분은 네트워크 현황에 따라 적응적으로 수축 또는 확장될 수 있어 PC 클라이언트는 최적화된 가상환경 상태정보를 제공받는다. 결론적으로, 제안된 모델은 다양한 컴퓨팅 환경의 PC 클라이언트에게 정확한 최우선 관심영역 정보를 제공한다.

• Journal of Information Management
• /
• v.25 no.1
• /
• pp.24-46
• /
• 1994

In this paper I will discuss definitions of hypermedia, multimedia and hypertext. Hypertext is the grouping of relevant information in the form of nodes. These nodes are then connected together through links. In the case of hypertext the nodes contain text or graphics. Multimedia is the combining of different media types for example sound, animation, text, graphics and video for the presentation of information by making use of computers. Hypermedia can be viewed as an extension of hypertext and multimedia. It is based on the concept of hypertext that uses nodes and links in the structuring of information in the system. In this case the nodes consist of an the different data types that are mentioned in the multimedia definition above. The 'node-and-link' concept is used in organisation of the information in hypermedia systems. The 'book' metaphor is an example of the way these systems are implemented. This concept is explained and a few advantages and disadvantages of making use of hypermedia systems are discussed. A new approach for the development of hypermedia systems, namely the knowledge-based approach is now looked into. Joel Peing-Ling Loo proposed this approach because he thought that it is the most effective way for handling this kind of technology. A semantic-based hypermedia model is developed in this approach to formulate solutions for the restrictions in presenting information authoring, maintenance and retrieval. The knowledge-based presentation of information includes the use of conventional data structures. These data structures make use of frames(objects), slots and the inheritance theory that is also used in expert systems. Relations develop between the different objects as these objects are included in the database. Relations can also exist between frames by means of attributes that belong to the frames.