• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.343-346
• /
• 2020

개체명 인식은 주어진 문장 내에서 OOV(Out of Vocaburary)로 자주 등장하는 고유한 의미가 있는 단어들을 미리 정의된 개체의 범주로 분류하는 작업이다. 최근 개체명이 문장 내에서 OOV로 등장하는 문제를 해결하기 위해 외부 리소스를 활용하는 연구들이 많이 진행되었다. 본 논문은 의미역, 의존관계 분석에 한국어 어휘지도를 이용한 자질을 추가하여 성능 향상을 보인 연구들을 바탕으로 이를 한국어 개체명 인식에 적용하고 평가하였다. 실험 결과, 한국어 어휘지도를 활용한 자질을 추가로 학습한 모델이 기존 모델에 비해 평균 1.83% 포인트 향상하였다. 또한, CRF 단일 모델만을 사용했음에도 87.25% 포인트라는 높은 성능을 보였다.

• Digital Contents
• /
• no.9 s.76
• /
• pp.59-59
• /
• 1999

최근 초고속 인터넷 서비스의 대명사로 ADSL이 부상하고 있다. ADSL(Asymmetric Digital Subscriber Line)은 '비대칭형 디지털 가입자망'으로 기존 전화선을 통해 일반 음성통화는 물론 데이터 통신을 초고속으로 이용할 수 있는 기술이다. ADSL의 의미와 국내 서비스 현황에 대해 살펴본다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.757-759
• /
• 2004

유전자 발현은 유전자가 mRNA와 생체의 기능을 일으키게 하는 단백질을 만들어내는 과정이다. 유전자 발현에 대한 정보는 유전자의 기능을 밝히고 유전자간의 상관 관계를 알아내는데 중요한 역할을 한다. 이러한 유전자 발현 연구를 위한 정보를 대량으로 신속하게 얻을 수 있는 도구가 DNA Chip이다. DNA Chip으로 얻은 수백-수천 개의 데이터는 그 데이터만으로는 의미를 갖지 못한다. 따라서 유전자 발현 정도에 따라 수치적으로 획득된 데이터에서 의미적인 특성을 찾아내기 위해서는 클러스터링 방법이 필요하다. 본 논문에서는 수많은 유전자 데이터 중에서 주요 정보를 포함한 것으로 판단되는 유전자 데이터를 선택하여 특징간을 계산하고 신경망 학습을 이용한 클러스터링하는 알고리즘에 대해서 기술한다.

• Journal of KIISE:Software and Applications
• /
• v.37 no.1
• /
• pp.60-73
• /
• 2010

This paper aims to describe KorLexClas 1.5 which provides us with a very large list of Korean numeral classifiers, and with the co-occurring noun categories that select each numeral classifier. Differently from KorLex of other POS, of which the structure depends largely on their reference model (Princeton WordNet), KorLexClas 1.0 and its extended version 1.5 adopt a direct building method. They demand a considerable time and expert knowledge to establish the hierarchies of numeral classifiers and the relationships between lexical items. For the efficiency of construction as well as the reliability of KorLexClas 1.5, we use following processes: (1) to use various language resources while their cross-checking for the selection of classifier candidates; (2) to extend the list of numeral classifiers by using a shallow parsing techniques; (3) to set up the hierarchies of the numeral classifiers based on the previous linguistic studies; and (4) to determine LUB(Least Upper Bound) of the numeral classifiers in KorLexNoun 1.5. The last process provides the open list of the co-occurring nouns for KorLexClas 1.5 with the extensibility. KorLexClas 1.5 is expected to be used in a variety of NLP applications, including MT.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.48 no.2
• /
• pp.57-64
• /
• 2011

The NGN (Next Generation Network) means the kernel infrastructure technology to provide information and communication services which are able to be used at present and future when a ubiquitous computing era has been realized. In other words, NGN can be the frame providing the same information and communication services anytime and anywhere regardless of wire and wireless. The broadband convergence network that has been built in the public institution has established a broadband multimedia communication network supporting voice telephone, task net, internet network, video conference network, voice over IP (VoIP) network and etc. It is possible for a requested bandwidth and services to be served, only if a broadband convergence network provide the interoperability between the various classes which include a transport network layer, network control layer, service control layer and other layers. In this paper, we analyzed the interoperability issues of the present broadband convergence network and propose a guideline for the future one.

• The Journal of the Convergence on Culture Technology
• /
• v.4 no.1
• /
• pp.275-278
• /
• 2018

This study examines how poem and poetic ego of Cho Ji-Hoon form synapses. It is to clarify the synaptic structure of the healing, the contact point between the literary mechanism and the mechanism of the ego. Therefore, it aims to encode the active therapy by substituting the structure into the literary therapy program. Cho Ji-Hoon's poem "Bellflower Flower" is a mesh of poem, and a mesh of semantic arguments is set up for the 'Bellflower Flower' of functor. At this time, the longing that attracts depression to the net of the semantic argument is caught. This exists as a function of healing. If we embody a literary therapy program that utilizes the synaptic structure of this healing, it will be able to experience the function of literary therapy improved than before.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1995.04a
• /
• pp.329-336
• /
• 1995

망구축 비용을 줄이고 이미 설치되어 있는 시설을 효율적으로 이용하는 관점에서 기존의 관로망을 이용하여 생존도가 보장되는 동기식 광전송망을 구축하는 설계기법에 대하여 연구하였다. 생존도를 보장하기 위해 물리망(physical network)과 논리망(logical network)을 함께 고려하여 관로망의 토폴로지가 이중연결도를 만족하도록 해야 한다. 이때 기존의 관로망에서 단순히 연결점으로 이용되는 지점을 접합 노드라고 하였으며 이 접합 노드를 설계시 고려하는 것이 현실적인 의미에서의 생존도를 보장할 수 있음을 보였다. 생존도가 보장된 동기식 광전송망을 설계하기 위한 설계절차를 제시하였으며 이를 이용하여 모델망을 설계하여 보았다. 모델망 설계시 접합 노드를 고려하였으며, 이러한 접근 방법이 기존 시설을 활용할 수 있어 망구축 비용을 감소시킬수 있음을 보였다.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.2
• /
• pp.113-120
• /
• 2024

The population sparseness index(PSI) is being utilized to describe the functioning of internal layers in artificial neural networks from the perspective of neurons, shedding light on the black-box nature of the network's internal operations. There is research indicating a positive correlation between the PSI and performance in each layer of convolutional neural network models for image classification. In this study, we observed the internal operations of a convolutional neural network when adversarial examples were applied. The results of the experiments revealed a similar pattern of positive correlation for adversarial examples, which were modified to maintain 5% accuracy compared to applying benign data. Thus, while there may be differences in each adversarial attack, the observed PSI for adversarial examples demonstrated consistent positive correlations with benign data across layers.

• Journal of KIISE
• /
• v.45 no.1
• /
• pp.94-98
• /
• 2018

We propose Wide Inception ResNet (WIR Net) an optimized neural network architecture as a real-time semantic segmentation method for autonomous driving. The neural network architecture consists of an encoder that extracts features by applying a residual connection and inception module, and a decoder that increases the resolution by using transposed convolution and a low layer feature map. We also improved the performance by applying an ELU activation function and optimized the neural network by reducing the number of layers and increasing the number of filters. The performance evaluations used an NVIDIA Geforce GTX 1080 and TX1 boards to assess the class and category IoU for cityscapes data in the driving environment. The experimental results show that the accuracy of class IoU 53.4, category IoU 81.8 and the execution speed of $640{\times}360$, $720{\times}480$ resolution image processing 17.8fps and 13.0fps on TX1 board.

• Journal of the Institute of Convergence Signal Processing
• /
• v.1 no.1
• /
• pp.32-41
• /
• 2000

In this paper, we proposed a method which predict the verb by using the neural network in order to enhance communication rate in augmentative communication system for Korean language disorders. Each word is represented by an information vector according to syntax and semantics, and is positioned at the state space by being partitioned into various regions different from a dictionary-like lexicon. Conceptual similarity is realized through position in state space. When a symbol was pressed, we could find the word for the symbol at the position in the state space. In order to prevent verb prediction's redundancy according to input units, we predicted the verb after separating class using the neural network. In the result we can enhance $20\% communication rate in the restricted space