• ETRI Journal
• /
• v.45 no.1
• /
• pp.93-104
• /
• 2023

Coreference resolution is a task in discourse analysis that links several headwords used in any document object. We suggest pointer networks-based coreference resolution for Korean using multi-task learning (MTL) with an attention mechanism for a hierarchical structure. As Korean is a head-final language, the head can easily be found. Our model learns the distribution by referring to the same entity position and utilizes a pointer network to conduct coreference resolution depending on the input headword. As the input is a document, the input sequence is very long. Thus, the core idea is to learn the word- and sentence-level distributions in parallel with MTL, while using a shared representation to address the long sequence problem. The suggested technique is used to generate word representations for Korean based on contextual information using pre-trained language models for Korean. In the same experimental conditions, our model performed roughly 1.8% better on CoNLL F1 than previous research without hierarchical structure.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.8
• /
• pp.319-330
• /
• 2021

Recently, in the field of open domain natural language question answering, multi-task, multi-hop question answering has been studied extensively. In this paper, we propose a novel deep neural network model using hierarchical graphs to answer effectively such multi-task, multi-hop questions. The proposed model extracts different levels of contextual information from multiple paragraphs using hierarchical graphs and graph neural networks, and then utilize them to predict answer type, supporting sentences and answer spans simultaneously. Conducting experiments with the HotpotQA benchmark dataset, we show high performance and positive effects of the proposed model.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.350-353
• /
• 2007

복잡하고 다원화되어 있는 재택건강관리 계획 모델링을 계층적 작업 네트워크 계획을 기반으로 설계하여 분산 네트워크의 성능을 최대한으로 활용한 자동화 계획 설계를 제안하였다. 이를 위하여 SHOP라는 계층적 작업 도구를 이용하여 응급, 주의, 비정상, 정상과 같은 4가지 시나리오 모델에 따른 맞춤형 건강관리 계획 설계를 구현하여 재택건강관리 시스템의 상태분류에 대한 보조 의사 결정 도구로써 적용하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.11
• /
• pp.3638-3657
• /
• 2022

In urban vehicular edge computing (VEC) environments, one edge server always serves many task requests in its coverage which results in the resource-constrained problem. To resolve the problem and improve system utilization, we first design a general hierarchical resource management framework based on typical VEC network structures. Following the framework, a specific interacting protocol is also designed for our decision algorithm. Secondly, a greedy bidding-based multi-hop task scheduling decision algorithm is proposed to realize effective task scheduling in resource-constrained VEC environments. In this algorithm, the goal of maximizing system utility is modeled as an optimization problem with the constraints of task deadlines and available computing resources. Then, an auction mechanism named greedy bidding is used to match task requests to edge servers in the case of multiple hops to maximize the system utility. Simulation results show that our proposal can maximize the number of tasks served in resource constrained VEC networks and improve the system utility.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.707-710
• /
• 2005

In this paper, we propose a new communication network for on-chip communication. The network is based on a direct sequence code division multiple access (DS-CDMA) technique. The new communication network is suitable for a parallel processing system and also drastically reduces the I/O pin count. Our network architecture is mainly divided into a CDMA-based network interface (CNI), a communication channel, a synchronizer. The network includes a reverse communication channel for reducing latency. The network decouples computation task from communication task by the CNI. An extreme truncation is considered to simplify the communication link. For the scalability of the network, we use a PN-code reuse method and a hierarchical structure. The network elements have a modular architecture. The communication network is done using fully synthesizable Verilog HDL to enhance the portability between process technologies.

• The KIPS Transactions:PartB
• /
• v.16B no.6
• /
• pp.489-496
• /
• 2009

Hierarchical Task Network(HTN) planning, a typical planning method for effectively taking advantage of domain-specific control knowledge, has been widely used in complex real applications for a long time. However, it still lacks theoretical formalization and standardization, and so there are some differences among existing HTN planners in terms of principle and performance. In this paper, we present an effective way to translate a HTN planning domain specification into the corresponding standard PDDL specification. Its main advantage is to allow even many domain-independent classical planners to utilize domain-specific control knowledge contained in the HTN specifications. In this paper, we try our translation-based approach to three different domains such as Blocks World, Office Delivery, Hanoi Tower, and then conduct some experiments with a forward-chaining heuristic state-space planner, FF, to analyze the efficiency of our approach.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.11 s.353
• /
• pp.35-43
• /
• 2006

In this paper we have presented a network based high-speed handover protocol using NetLMM(Network based Localized Mobility Management) WG protocol in IETF(Internet Engineering Task Force). We use IEEE 802.21 MIHS(Media Independent Handover Services) for improving handover latency and we analysis proposed Fast NetLMM protocol performance using Fluid Flow Mobility Model. Evaluation results show that the Fast NetLMM protocol performance is better than other mobility management protocols.

• Journal of the Korean Society of Safety
• /
• v.15 no.2
• /
• pp.36-45
• /
• 2000

Automated production system is composed of many complicated techniques and it become a very difficult task to control, monitor and diagnose this compound system. Moreover, it is required to develop an effective diagnosing technique and reduce the diagnosing time while operating the system in parallel under many faults occurring concurrently. This study develops a Modular Artificial Neural Network(MANN) which can perform a diagnosing function of multiple faults with the following steps: 1) Modularizing a complicated system into subsystems. 2) Formulating a hierarchical structure by dividing the subsystem into many detailed elements. 3) Planting an artificial neural network into hierarchical module. The system developed is implemented on workstation platform with $X-Windows^{(r)}$ which provides multi-process, multi-tasking and IPC facilities for visualization of transaction, by applying the software written in $ANSI-C^{(r)}$ together with $MOTIF^{(r)}$ on the fault diagnosis of PI feedback controller reactor. It can be used as a simple stepping stone towards a perfect multiple diagnosing system covering with various industrial applications, and further provides an economical approach to prevent a disastrous failure of huge complicated systems.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.7B
• /
• pp.668-676
• /
• 2009

Hierarchical Mobile 1Pv6(HM1Pv6) have been proposed by IETF(Internet Engineering Task Force) beginning from Mobile 1Pv6 for mobility support in IP networks, however these researches relying on client based mobility support have not been drawn attention due to excessive consumption of wireless resources and long handover delay. In this paper, we propose the Router-based Binding Update(RBU) scheme to solve problems in existing client-based mobility support schemes. The router registers location information of mobile nodes through Neighbor Discovery protocol without additional codes for the RBU scheme to a terminal operated by existing HMlPv6. By using this the RBU scheme is designed so that it can support partial nupport based mobility and reduce handover latency rather than using HMIPv6. It is analysed and compared with existing HMIPv6 to verify efficiency of the RBU scheme. As a result, the RBU scheme has outperformed existing HMIPv6 by 15% in terms of macro handover delay especially when long delay on wireless links exists.

• Journal of Internet Computing and Services
• /
• v.12 no.4
• /
• pp.15-26
• /
• 2011

As quick and secure mobility service is becoming a critical issue in the ubiquitous environment. Internet Engineering Task Force (IETF) has done a lot of meaningful work in order to cope with the critical issues, which is a key technology of guaranteeing the legally and safely using of network resources, they has proposed Hierarchical Mobile IPv6 (HMIPv6) to complement for such problems as handover latency and signaling overhead in existing MIPv6. Most of the current research about HMIPv6 focuses on how to optimize the interactive processes between the HMIPv6 and AAA (Authentication, Authorization, Accounting) protocol. This paper describes a cost-effective hierarchical authentication scheme, which makes its focus on minimizing the authentication latency in AAA processing. In this scheme, a hierarchical AAA architecture is proposed, in which the AAA servers are deployed on the Mobility Anchor Point (MAP), the Root AAA server manages several Leaf AAA servers and the Brokers on behalf of the AAA server in home domain. The simulation results shows that the proposed scheme reduces the handoff and authentication latency evidently compared to the previous traditional authentication combination modeling.