• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.4
• /
• pp.169-178
• /
• 2022

Morphemes are most primitive units in a language that lose their original meaning when segmented into smaller parts. In Korean, a sentence is a sequence of eojeols (words) separated by spaces. Each eojeol comprises one or more morphemes. Korean morphological analysis (KMA) is to divide eojeols in a given Korean sentence into morpheme units. It also includes assigning appropriate part-of-speech(POS) tags to the resulting morphemes. KMA is one of the most important tasks in Korean natural language processing (NLP). Improving the performance of KMA is closely related to increasing performance of Korean NLP tasks. Recent research on KMA has begun to adopt the approach of machine translation (MT) models. MT is to convert a sequence (sentence) of units of one domain into a sequence (sentence) of units of another domain. Neural machine translation (NMT) stands for the approaches of MT that exploit neural network models. From a perspective of MT, KMA is to transform an input sequence of units belonging to the eojeol domain into a sequence of units in the morpheme domain. In this paper, we propose a deep learning model for KMA. The backbone of our model is based on the BERT-fused model which was shown to achieve high performance on NMT. The BERT-fused model utilizes Transformer, a representative model employed by NMT, and BERT which is a language representation model that has enabled a significant advance in NLP. The experimental results show that our model achieves 98.24 F1-Score.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.11 no.4
• /
• pp.113-118
• /
• 2011

Sequence homology analysis in the substances in the phenomenon of life is to create database by sorting and indexing and to demonstrate the usefulness of informatics. In this paper, Markov models are used in GenScan program to convert the pattern of complex eukaryotic protein sequences. It becomes impossible to navigate the minimum distance, complexity increases exponentially as the exact calculation. It is used scorecard in amino acid substitutions between similar amino acid substitutions to have a differential effect score, and is applied the Markov models sophisticated concealment of the transition probability model. As providing superior method to translate sequences homologous sequences in analysis using blast p, Markov models. is secreted protein structure of sequence translations.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2001.04a
• /
• pp.422-425
• /
• 2001

The realization of the avoidance, decrease and utilization of waste can be made through reduction of resource consumption during product production and use. Beside that it is desirable to regain the resource attached to products and components. The same resources can be much used in product and mater all cycle through their reuse and regeneration In order to improve the use productivity of resource the disassembly make up the substantial prerequisite. In this paper a model describing the disassembly sequence structure is introduced under consideration of the influential facts related to disassembly process planning rules for disassembly sequence planning are derived from that.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.5
• /
• pp.783-788
• /
• 2002

Recently, research and developmental direction of communication system is concurrent adopting voice data and face image in speaking to provide more higher recognition rate then in the case of only voice data. Therefore, we present a method of lipreading in speech image sequence by using the 3-D facial shape model. The method use a feature information of the face image such as the opening-level of lip, the movement of jaw, and the projection height of lip. At first, we adjust the 3-D face model to speeching face Image sequence. Then, to get a feature information we compute variance quantity from adjusted 3-D shape model of image sequence and use the variance quality of the adjusted 3-D model as recognition parameters. We use the intensity inclination values which obtaining from the variance in 3-D feature points as the separation of recognition units from the sequential image. After then, we use discrete HMM algorithm at recognition process, depending on multiple observation sequence which considers the variance of 3-D feature point fully. As a result of recognition experiment with the 8 Korean vowels and 2 Korean consonants, we have about 80% of recognition rate for the plosives md vowels.

• Korean Journal of Cognitive Science
• /
• v.18 no.1
• /
• pp.1-14
• /
• 2007

In a goal-oriented dialogue, speakers' intentions can be represented by domain actions that consist of pairs of a speech act and a concept sequence. Therefore, if we plan to implement an intelligent dialogue system, it is very important to correctly infer the domain actions from surface utterances. In this paper, we propose a statistical model to determine speech acts and concept sequences using conditional random fields at the same time. To avoid biased learning problems, the proposed model uses low-level linguistic features such as lexicals and parts-of-speech. Then, it filters out uninformative features using the chi-square statistic. In the experiments in a schedule arrangement domain, the proposed system showed good performances (the precision of 93.0% on speech act classification and the precision of 90.2% on concept sequence classification).

• 한국어정보학회:학술대회논문집
• /
• 2016.10a
• /
• pp.300-304
• /
• 2016

본 논문에서는 한국어 의미역 결정을 순차열 분류 문제(Sequence Labeling Problem)가 아닌 순차열 변환 문제(Sequence-to-Sequence Learning)로 접근하였고, 구문 분석 단계와 자질 설계가 필요 없는 End-to-end 방식으로 연구를 진행하였다. 음절 단위의 RNN Search 모델을 사용하여 음절 단위로 입력된 문장을 의미역이 달린 어절들로 변환하였다. 또한 순차열 변환 문제의 성능을 높이기 위해 연구된 인풋-피딩(Input-feeding) 기술과 카피넷(CopyNet) 기술을 한국어 의미역 결정에 적용하였다. 실험 결과, Korean PropBank 데이터에서 79.42%의 레이블 단위 f1-score, 71.58%의 어절 단위 f1-score를 보였다.

• Annual Conference on Human and Language Technology
• /
• 2016.10a
• /
• pp.300-304
• /
• 2016

본 논문에서는 한국어 의미역 결정을 순차열 분류 문제(Sequence Labeling Problem)가 아닌 순차열 변환 문제(Sequence-to-Sequence Learning)로 접근하였고, 구문 분석 단계와 자질 설계가 필요 없는 End-to-end 방식으로 연구를 진행하였다. 음절 단위의 RNN Search 모델을 사용하여 음절 단위로 입력된 문장을 의미역이 달린 어절들로 변환하였다. 또한 순차열 변환 문제의 성능을 높이기 위해 연구된 인풋-피딩(Input-feeding) 기술과 카피넷(CopyNet) 기술을 한국어 의미역 결정에 적용하였다. 실험 결과, Korean PropBank 데이터에서 79.42%의 레이블 단위 f1-score, 71.58%의 어절 단위 f1-score를 보였다.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2015.11a
• /
• pp.196-197
• /
• 2015

In tall building construction, time for transporting form affects formwork duration as plan size has become larger and quantity of inputted form has been increased. Thus, necessity of systematic dismantlement sequence of form has been increased to reduce the duration of formwork. Tabu search has been efficiently applied to solve problem of combinatorial optimization by using tabu list which can improve combination values. Therefore, this study proposes optimization model of dismantlement sequence of table form which has been preferred in tall building construction, to reduce the formwork duration by minimizing time for transporting form.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2008.04a
• /
• pp.265-268
• /
• 2008

In this paper behavior of U-Channel Bridge (UCB) and the slab design considering construction sequence was studied. The segments of UCB are produced in the factory and transported to the site by trailers, and the segments are fabricated in the construction field. In this sequence the supporting conditions are changed. Four steps that were the segment precasting step, the segment carrying step, the segment placed on the erection beam step, and the completion step were chosen by supporting condition. In each step model using the frame and plate elements was proposed and structural analysis was performed. Four construction steps were to be considered in the process of slab analysis. The design method of slab was proposed considering construction sequence.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.21 no.6
• /
• pp.105-114
• /
• 1984

A fast pseudo-noise (PN) sequence acquisition algorithm for the direct-sequence (DS) spread spectrum system is proposed. The basic concept of the algorithm has been adopted from that of the classical sliding correlator. Mathematical modeling, analysis and computer simulation of the proposed system have been done. The results of analysis and computer simulation show that the acquisition system yields a significant performance improvement over the sliding correlator. Its acquisition time takes only 45 ms when signal-to-noise ratio(SNR) is -18dB. The algorithm developed has been implemented in hardware and its experimental result is also given.