• Journal of KIISE:Software and Applications
• /
• v.34 no.2
• /
• pp.140-149
• /
• 2007

This paper presents a statistical model for Korean dependency-based parsing. Although Korean is one of free word order languages, it has the feature of which some word order is preferred to local contexts. Earlier works proposed parsing models using modification lengths due to this property. Our model uses headible path contexts for modification length probabilities. Using a headible path of a dependent it is effective for long distance relation because the large surface context for a dependent are abbreviated as its headible path. By combined with lexical bigram dependency, our probabilistic model achieves 86.9% accuracy in eojoel analysis for KAIST corpus, more improvement especially for long distance dependencies.

• Journal of KIISE:Computer Systems and Theory
• /
• v.26 no.9
• /
• pp.1158-1165
• /
• 1999

조건부 분기 명령어(conditional branch instruction)의 잘못된 분기 예측(branch misprediction)은 프로세서의 성능 향상에 심각한 장애 요인이 되고 있다. 특히 시분할(time-sharing) 시스템과 같이 문맥 교환(context switch)이 발생하는 멀티프로그래밍 환경(multiprogramming environment)에서는 더욱 낮은 분기 예측 정확성(branch prediction accuracy)을 보인다. 본 논문에서는 문맥 교환이 발생하는 멀티프로그래밍 환경에서 높은 분기 예측 정확성을 보이는 중첩 분기 예측표 교환(Overlapped Predictor Table Switch, OPTS) 기법을 소개한다. 분기 예측표(predictor table)를 분할하여 각각의 프로세스(process)에 할당하는 OPTS 기법은 문맥 교환의 영향을 최소화함으로써 높은 분기 예측 정확성을 유지하는 분기 예측 방법이다.Abstract There is wide agreement that one of the most important impediments to the performance of current and future pipelined superscalar processors is the presence of conditional branches in the instruction stream. Accurate branch prediction is required to overcome this performance limitation. Many branch predictors have been proposed to help to alleviate this problem, including the two-level adaptive branch predictor, and more recently, hybrid branch predictor. In a less idealized environment, such as a time-sharing system, code of interest involves context switches. Context switches, even at fairly large intervals, can seriously degrade the performance of many of the most accurate branch prediction schemes. In this study, we measure the effect of context switch on the branch prediction accuracy in various situation and show the feasibility of our new mechanism, OPTS(Overlapped Predictor Table Switch), which save and restore branch history table at every context switch.

• Journal of KIISE:Computer Systems and Theory
• /
• v.29 no.11
• /
• pp.611-621
• /
• 2002

For real-time systems, multiprocessor support is indispensable to handle the large number of requests. Existing real-time on-line scheduling algorithms such as Earliest Deadline First Algorithm (EDF) and Least Laxity Algorithm (LLA) may not be suitable for scheduling real-time tasks in multiprocessor systems. Although EDF has low context switching overhead, it suffers from "multiple processor anomalies." LLA has been shown as suboptimal, but has the potential for higher context switching overhead. Earliest Deadline Zero Laxity (EDZL) solved somewhat the problems of those algorithms, however is suboptimal for only two processors. Another algorithm EDA2 shows very good performance in overload phase, however, is not suboptimal for muitiprocessors. We propose two on-line scheduling algorithms, Earliest Deadline/Least Laxity (ED/LL) and ED2/LL. ED/LL is suboptimal for multiprocessors, and has low context switching overhead and low deadline miss rate in normal load phase. However, ED/LL is ineffective when the system is overloaded. To solve this problem, ED2/LL uses ED/LL or EDZL in normal load phase and uses EDA2 in overload phase. Experimental results show that ED2/LL achieves good performance in overload phase as wet] as in normal load phase.oad phase.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.6
• /
• pp.378-387
• /
• 2007

To enhancing the exercise effect, exercise management systems are introduced and generally used. They create the proper exercise program through exercise prescription after determining the personal body status. When the exercise programs are created, they will consider $2weeks{\sim}3months$ period. And, existing exercise programs cannot respect with personal exercise habits or exercise period which are changing variedly. If exercise period is long, it can be caused inappropriate exercise about user current status. To solve these problems in legacy systems, this paper proposes a Context Aware Exercise Model (CAEM) to provide the exercise program considering the user context. Also, we implemented that as Intelligent Fitness Guide (IFG) System. The IFG system is selectively received necessary measurement values as input values according to user's context. If exercise kinds, frequency and strength of user are changing, that system creates the exercise program through exercise optimization algorithm and exercise knowledge base. As IFG is providing the exercise program in a real time, it can be managed the effective exercise according to user context.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.7
• /
• pp.259-266
• /
• 2018

In this paper, we propose a method to classify a document using a Recurrent Neural Network by extracting features considering word sense and contexts. Word2vec method is adopted to include the order and meaning of the words expressing the word in the document as a vector. Doc2vec is applied for considering the context to extract the feature of the document. RNN classifier, which includes the output of the previous node as the input of the next node, is used as the document classification method. RNN classifier presents good performance for document classification because it is suitable for sequence data among neural network classifiers. We applied GRU (Gated Recurrent Unit) model which solves the vanishing gradient problem of RNN. It also reduces computation speed. We used one Hangul document set and two English document sets for the experiments and GRU based document classifier improves performance by about 3.5% compared to CNN based document classifier.

• The Journal of Bigdata
• /
• v.5 no.1
• /
• pp.197-208
• /
• 2020

Lexical ambiguity means that a word can be interpreted as two or more meanings, such as homonym and polysemy, and there are many cases of word sense ambiguation in words expressing emotions. In terms of projecting human psychology, these words convey specific and rich contexts, resulting in lexical ambiguity. In this study, we propose an emotional classification model that disambiguate word sense using bidirectional LSTM. It is based on the assumption that if the information of the surrounding context is fully reflected, the problem of lexical ambiguity can be solved and the emotions that the sentence wants to express can be expressed as one. Bidirectional LSTM is an algorithm that is frequently used in the field of natural language processing research requiring contextual information and is also intended to be used in this study to learn context. GloVe embedding is used as the embedding layer of this research model, and the performance of this model was verified compared to the model applied with LSTM and RNN algorithms. Such a framework could contribute to various fields, including marketing, which could connect the emotions of SNS users to their desire for consumption.

• Proceedings of the Korean Society for Cognitive Science Conference
• /
• 2000.06a
• /
• pp.292-299
• /
• 2000

본 논문에서는 개체명 사전과 결합 단어 사전, 그리고 용언의 하위범주화 사전을 이용하는 규칙기반의 한국어 개체명 인식 방법을 제안한다. 각 규칙은 네 단계로 나누어 적용하는데, 첫번째 단계에서는 어절 내의 단어 정보를, 두번째 단계에서는 제한된 주변 문맥 정보를, 그리고 세번째 단계에서는 용언의 하위범주화 정보와 개체명과의 관계를 이용하고, 마지막으로 네번째 단계에서는 개체명 간의 관계 정보를 고려한다. 본 논문에서 제안한 규칙 기반 개체명 인식기의 성능을 평가하기 위해 실험한 결과 90.4%의 정확률과 83.4%의 재현율을 얻었다.

• Proceedings of the Korean Society for Cognitive Science Conference
• /
• 2000.06a
• /
• pp.68-75
• /
• 2000

상대방에게 의사를 전달할 때 보다 정확하게 자신의 의도를 표현하려면 대화의 흐름에 맞는 적절한 억양을 주어 발화해야 한다. 본 논문에서는 결함범주문법을 이용하여 문장을 분석하고 문장 내 정보와 문장 간 정보 즉, 문맥에 따라 강세(pitch accent), 휴지(pause), 강조 등의 억양정보를 어떻게 나타내야 하는지를 분석하여 문장의 정보구조에 추가하는 방법을 제시한다.

• The KIPS Transactions:PartD
• /
• v.11D no.5
• /
• pp.1049-1062
• /
• 2004

With the popularization of a World Wide Web (WWW), the quantity of web information has been increased. Therefore, an efficient searching system is needed to offer the exact result of diverse Information to user. Due to this reason, it is important to extract and analysis of user requirements in the distributed information environment. The conventional searching method used the only keyword for the web searching. However, the searching method proposed in this paper adds the context information of keyword for the effective searching. In addition, this searching method extracts keywords by the new keyword extraction method proposed in this paper and it executes the web searching based on a keyword mining profile generated by the extracted keywords. Unlike the conventional searching method which searched for information by a representative word, this searching method proposed in this paper is much more efficient and exact. This is because this searching method proposed in this paper is searched by the example based query included content information as well as a representative word. Moreover, this searching method makes a domain keyword list in order to perform search quietly. The domain keyword is a representative word of a special domain. The performance of the proposed algorithm is analyzed by a series of experiments to identify its various characteristic.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.5
• /
• pp.477-481
• /
• 2008

Place recognition is necessary for a mobile user to be provided with place-dependent information. This paper proposes real-time video based place recognition system that identifies users' current place while moving in the building. As for the feature extraction of a scene, there have been existing methods based on global feature analysis that has drawback of sensitive-ness for the case of partial occlusion and noises. There have also been local feature based methods that usually attempted object recognition which seemed hard to be applied in real-time system because of high computational cost. On the other hand, researches using statistical methods such as HMM(hidden Markov models) or bayesian networks have been used to derive place recognition result from the feature data. The former is, however, not practical because it requires huge amounts of efforts to gather the training data while the latter usually depends on object recognition only. This paper proposes a combined approach of global and local feature analysis for feature extraction to complement both approaches' drawbacks. The proposed method is applied to a mobile information system and shows real-time performance with competitive recognition result.