• Journal of the Korea Society of Computer and Information
• /
• v.17 no.12
• /
• pp.111-120
• /
• 2012

As the P2P System is a distributed system that shares resources of nodes that participate in the system, all the nodes serve as a role of server and client. Currently, although systematic, structured P2P systems such as Chord, Pastry, and Tapestry were suggested based on the distributed hash table, these systems are limited to $log_2N$ for performance efficiency. For this enhanced performance efficiency limited, the article herein suggests group routing algorithm. The suggested algorithm is a node-to-group routing algorithm which divides circular address space into groups and uses a concept of pointer representing each group, which is an algorithm where routing is performed based on pointer. To evaluate algorithm performance, a comparative analysis was conducted on average hops, routing table size, and delayed transmission for chord and routing, a signature algorithm in P2P systems. Therefore, enhanced performance is verified for comparative items from the simulation results.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.535-539
• /
• 2020

다양한 발화를 모델링하는 요구는 자연어 처리 분야에서 꾸준히 있었으며 단어, 구 또는 문장과 동등한 의미 콘텐츠를 자동으로 식별하고 생성하는 것은 자연어 처리의 중요한 부분이다. 본 논문에서는 포인터 생성 네트워크(Pointer Generate Nework)를 이용하여 패러프레이즈 생성 모델을 제안한다. 제안한 모델의 성능을 측정하기 위해 사람이 직접 구축한 유사 문장 코퍼스를 이용하였으며, 토큰 단위의 BLEU-4 0.250, ROUGE_L 0.455, CIDEr 2.190의 성능을 보였다. 하지만 입력 문장과 동일한 문장을 출력하는 문제점이 존재하여 빔서치(beam search)를 적용하여 입력 문장과 비교하여 생성 문장을 선택하는 방식을 적용하였다. 입력 문장과 동일한 문장을 제외한 문장으로 평가를 진행했으며, 토큰 단위의 BLEU-4 0.234, ROUGE_L 0.459, CIDEr 2.041의 성능을 보였으나, 패러프레이즈 생성 데이터 양이 크게 증가하였다. 본 연구는 문장 간의 의미적으로 동일한 정보를 정확하게 추출할 수 있게 됨으로써 정보 추출, 온톨로지 생성에 도움이 될 것이다. 또한 이러한 기법이 챗봇에서 사용자의 의도 탐지 및 MRC와 같은 자연어 처리의 여러 분야에 유용한 자원으로 사용될 것이다.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.239-242
• /
• 2018

문맥 표현은 Recurrent neural network (RNN)에 기반한 언어 모델을 학습하여 얻은 여러 층의 히든 스테이트(hidden state)를 가중치 합(weighted sum)을 하여 얻어낸 벡터이다. Convolution neural network (CNN)를 이용하여 음절 표현을 학습하는 경우, 데이터 내에서 발생하는 미등록어를 처리할 수 있다. 본 논문에서는 음절 표현 CNN 기반의 포인터 네트워크와 문맥 표현을 함께 이용하는 방법을 제안하고, 이를 상호참조해결에 적용한다. 실험 결과, 질의응답 데이터셋에서 CoNLL F1 57.88%로 규칙기반에 비하여 11.09% 더 좋은 성능을 보였다.

• Proceedings of the IEEK Conference
• /
• 2002.06a
• /
• pp.417-420
• /
• 2002

In this paper, we implemented a SDH synchronous network system based on ITU-T recommendation G.707 - Network node interface for the synchronous digital archy(SDH). For the system, we used signal processing SDH ASIC, and designed a FPGA_Control chip for various signal control and a FPGA_Alignment cllip for data alignment using YHDL(Very high speed integrated circuit Hardware Description Language). For system monitoring, an operation system was developed using ANSI C and executed in CPU (Motorola MPC-860). The system was evaluated by using ANT-20 for data transmission error defection, jitter detection, pointer chocking, and overhead determination.

• ETRI Journal
• /
• v.43 no.6
• /
• pp.1038-1048
• /
• 2021

We propose an end-to-end neural coreference resolution for the Korean language that uses an attention mechanism to point to the same entity. Because Korean is a head-final language, we focused on a method that uses a pointer network based on the head. The key idea is to consider all nouns in the document as candidates based on the head-final characteristics of the Korean language and learn distributions over the referenced entity positions for each noun. Given the recent success of applications using bidirectional encoder representation from transformer (BERT) in natural language-processing tasks, we employed BERT in the proposed model to create word representations based on contextual information. The experimental results indicated that the proposed model achieved state-of-the-art performance in Korean language coreference resolution.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.8
• /
• pp.315-324
• /
• 2022

In this paper, we propose KoEPT, a Transformer-based generative model for automatic math word problems solving. A math word problem written in human language which describes everyday situations in a mathematical form. Math word problem solving requires an artificial intelligence model to understand the implied logic within the problem. Therefore, it is being studied variously across the world to improve the language understanding ability of artificial intelligence. In the case of the Korean language, studies so far have mainly attempted to solve problems by classifying them into templates, but there is a limitation in that these techniques are difficult to apply to datasets with high classification difficulty. To solve this problem, this paper used the KoEPT model which uses 'expression' tokens and pointer networks. To measure the performance of this model, the classification difficulty scores of IL, CC, and ALG514, which are existing Korean mathematical sentence problem datasets, were measured, and then the performance of KoEPT was evaluated using 5-fold cross-validation. For the Korean datasets used for evaluation, KoEPT obtained the state-of-the-art(SOTA) performance with 99.1% in CC, which is comparable to the existing SOTA performance, and 89.3% and 80.5% in IL and ALG514, respectively. In addition, as a result of evaluation, KoEPT showed a relatively improved performance for datasets with high classification difficulty. Through an ablation study, we uncovered that the use of the 'expression' tokens and pointer networks contributed to KoEPT's state of being less affected by classification difficulty while obtaining good performance.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.682-684
• /
• 2018

구문 분석은 문장을 구성하는 단어들 간의 관계를 알아내 문장의 구조를 분석하는 작업이다. 구문 분석은 구구조 분석과 의존 구문 분석으로 나누어지는데 한국어처럼 어순이 자유로운 언어는 의존 구문 분석이 적합하다. 최근 구문 분석은 심층 신경망을 적용한 방식이 중점적으로 연구되고 있으며, 포인터 네트워크를 사용하는 모델이 가장 좋은 성능을 보였다. 그러나 포인터 네트워크만으로 구문적인 정보를 학습하기에는 한계가 있다. 본 논문에서는 멀티헤드 어텐션을 함께 사용하여 포인터 네트워크만을 사용 했을 때보다 높은 성능(UAS 92.85%, LAS 90.65%)을 보였다.

• Proceedings of the IEEK Conference
• /
• 2001.06a
• /
• pp.261-264
• /
• 2001

This paper relates to a node structure of a multiway search tree and a search method using the node structure and, more particularly, to a search method for accelerating its search speed by reducing the depth of each small tree in a multi-way search tree. The proposed idea can increase the number of keys capable of being recorded on a cache line by using one pointer at a node of the multi-way search tree so that the number of branches in a network address search is also increased and thus the tree depth is reduced. As a result, this idea can accelerate the search speed and the speed of the forwarding engine and accomplish a further speed-up by decreasing required memories and thus increasing a memory rate.

• Proceedings of the KIEE Conference
• /
• 2003.11c
• /
• pp.608-611
• /
• 2003

A large part of the embedded system, compared with the PC, have low performance CPU and small memory. So the embedded operating system fits the condition of that hardware system. A Single Address Space (SAS) OS has the operating system and all applications in the single address space. The SAS architecture enhances sharing and co-operation, because addresses have a unique interpretation. Thus, pointer-based date structures can be directly communicated and shared between programs at any time, and can be stored directly on storage. The key point of the SAS OS on the embedded system is the low overhead inter-action between programs in process and usage. So SAS OS can be ported on the low performance CPU. In this paper, we design the SAS OS (named emNOS, Embedded Network Operating System) on the ARMTTDMI processor. Finally we show the benefits of the SAS OS on the embedded system.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.93-97
• /
• 2020

본 연구는 딥 러닝 기반 의존 구문 분석에서, 학습에 적용하는 손실 함수에 따른 성능을 평가하였다. Pointer Network를 이용한 Left-To-Right 모델을 총 세 가지의 손실 함수(Maximize Golden Probability, Cross Entropy, Local Hinge)를 이용하여 학습시켰다. 그 결과 LH 손실 함수로 학습한 모델이 선행 연구와 같이 MGP 손실 함수로 학습한 것에 비해 UAS/LAS가 각각 0.86%p/0.87%p 상승하였으며, 특히 의존 거리가 먼 경우에 대하여 분석 성능이 크게 향상됨을 확인하였다. 딥러닝 의존 구문 분석기를 구현할 때 학습모델과 입력 표상뿐만 아니라 손실 함수 역시 중요하게 고려되어야 함을 보였다.