• Title, Summary, Keyword: self-matching network

Search Result 24, Processing Time 0.047 seconds

S2-Net: Korean Machine Reading Comprehension with SRU-based Self-matching Network (S2-Net: SRU 기반 Self-matching Network를 이용한 한국어 기계 독해)

  • Park, Cheoneum;Lee, Changki;Hong, Sulyn;Hwang, Yigyu;Yoo, Taejoon;Kim, Hyunki
    • 한국어정보학회:학술대회논문집
    • /
    • /
    • pp.35-40
    • /
    • 2017
  • 기계 독해(Machine reading comprehension)는 주어진 문맥을 이해하고, 질문에 적합한 답을 문맥 내에서 찾는 문제이다. Simple Recurrent Unit (SRU)은 Gated Recurrent Unit (GRU)등과 같이 neural gate를 이용하여 Recurrent Neural Network (RNN)에서 발생하는 vanishing gradient problem을 해결하고, gate 입력에서 이전 hidden state를 제거하여 GRU보다 속도를 향상시킨 모델이며, Self-matching Network는 R-Net 모델에서 사용된 것으로, 자기 자신의 RNN sequence에 대하여 어텐션 가중치 (attention weight)를 계산하여 비슷한 의미 문맥 정보를 볼 수 있기 때문에 상호참조해결과 유사한 효과를 볼 수 있다. 본 논문에서는 한국어 기계 독해 데이터 셋을 구축하고, 여러 층의 SRU를 이용한 Encoder에 Self-matching layer를 추가한 $S^2$-Net 모델을 제안한다. 실험 결과, 본 논문에서 제안한 $S^2$-Net 모델이 한국어 기계 독해 데이터 셋에서 EM 65.84%, F1 78.98%의 성능을 보였다.

  • PDF

S2-Net: Machine reading comprehension with SRU-based self-matching networks

  • Park, Cheoneum;Lee, Changki;Hong, Lynn;Hwang, Yigyu;Yoo, Taejoon;Jang, Jaeyong;Hong, Yunki;Bae, Kyung-Hoon;Kim, Hyun-Ki
    • ETRI Journal
    • /
    • v.41 no.3
    • /
    • pp.371-382
    • /
    • 2019
  • Machine reading comprehension is the task of understanding a given context and finding the correct response in that context. A simple recurrent unit (SRU) is a model that solves the vanishing gradient problem in a recurrent neural network (RNN) using a neural gate, such as a gated recurrent unit (GRU) and long short-term memory (LSTM); moreover, it removes the previous hidden state from the input gate to improve the speed compared to GRU and LSTM. A self-matching network, used in R-Net, can have a similar effect to coreference resolution because the self-matching network can obtain context information of a similar meaning by calculating the attention weight for its own RNN sequence. In this paper, we construct a dataset for Korean machine reading comprehension and propose an $S^2-Net$ model that adds a self-matching layer to an encoder RNN using multilayer SRU. The experimental results show that the proposed $S^2-Net$ model has performance of single 68.82% EM and 81.25% F1, and ensemble 70.81% EM, 82.48% F1 in the Korean machine reading comprehension test dataset, and has single 71.30% EM and 80.37% F1 and ensemble 73.29% EM and 81.54% F1 performance in the SQuAD dev dataset.

S2-Net: Korean Machine Reading Comprehension with SRU-based Self-matching Network (S2-Net: SRU 기반 Self-matching Network를 이용한 한국어 기계 독해)

  • Park, Cheoneum;Lee, Changki;Hong, Sulyn;Hwang, Yigyu;Yoo, Taejoon;Kim, Hyunki
    • Annual Conference on Human and Language Technology
    • /
    • /
    • pp.35-40
    • /
    • 2017
  • 기계 독해(Machine reading comprehension)는 주어진 문맥을 이해하고, 질문에 적합한 답을 문맥 내에서 찾는 문제이다. Simple Recurrent Unit (SRU)은 Gated Recurrent Unit (GRU)등과 같이 neural gate를 이용하여 Recurrent Neural Network (RNN)에서 발생하는 vanishing gradient problem을 해결하고, gate 입력에서 이전 hidden state를 제거하여 GRU보다 속도를 향상시킨 모델이며, Self-matching Network는 R-Net 모델에서 사용된 것으로, 자기 자신의 RNN sequence에 대하여 어텐션 가중치 (attention weight)를 계산하여 비슷한 의미 문맥 정보를 볼 수 있기 때문에 상호참조해결과 유사한 효과를 볼 수 있다. 본 논문에서는 한국어 기계 독해 데이터 셋을 구축하고, 여러 층의 SRU를 이용한 Encoder에 Self-matching layer를 추가한 $S^2$-Net 모델을 제안한다. 실험 결과, 본 논문에서 제안한 $S^2$-Net 모델이 한국어 기계 독해 데이터 셋에서 EM 65.84%, F1 78.98%의 성능을 보였다.

  • PDF

Hybrid Neural Networks for Intrusion Detection System

  • Jirapummin, Chaivat;Kanthamanon, Prasert
    • Proceedings of the IEEK Conference
    • /
    • /
    • pp.928-931
    • /
    • 2002
  • Network based intrusion detection system is a computer network security tool. In this paper, we present an intrusion detection system based on Self-Organizing Maps (SOM) and Resilient Propagation Neural Network (RPROP) for visualizing and classifying intrusion and normal patterns. We introduce a cluster matching equation for finding principal associated components in component planes. We apply data from The Third International Knowledge Discovery and Data Mining Tools Competition (KDD cup'99) for training and testing our prototype. From our experimental results with different network data, our scheme archives more than 90 percent detection rate, and less than 5 percent false alarm rate in one SYN flooding and two port scanning attack types.

  • PDF

Location Awareness Method using Vector Matching of RSSI in Low-Rate WPAN (저속 WPAN에서 수신신호세기의 Vector Matching을 이용한 위치 인식 방식)

  • Nam Yoon-Seok;Choi Eun-Chang;Huh Jae-Doo
    • Journal of Information Technology Applications and Management
    • /
    • v.12 no.4
    • /
    • pp.93-104
    • /
    • 2005
  • Recently, RFID/USN is one of fundamental technologies in information and communications networks. Low-Rate WPAN, IEEE802.15.4 is a low-cost communication network that allows wireless connectivity in applications with limited Power and relaxed throughput requirements. Its applications are building automation, personal healthcare, industrial control, consumer electronics, and so on. Some applications require location information. Of course location awareness is useful to improve usability of data Low-Rate WPAN Is regarded as a key specification of the sensor network with the characteristics of wireless communication, computing, energy scavenging, self-networking, and etc. Unfortunately ZigBee alliance propose a lot of applications based on location aware technologies, but the specification and low-rate WPAN devices don't support anything about location-based services. RSSI ( Received Signal Strength indication) is for energy detection to associate, channel selection, and etc. RSSI is used to find the location of a potable device in WLAN. In this paper we studied indoor location awareness using vector matching of RSSI in low-Rate wireless PAN. We analyzed the characteristics of RSSI according to distance and experimented location awareness. We implemented sensor nodes with different shapes and configured the sensor network for the location awareness with 4 fixed nodes and a mobile node. We try to contribute developing location awareness method using RSSI in 3-dimension space.

  • PDF

VRML image overlay method for Robot's Self-Localization (VRML 영상오버레이기법을 이용한 로봇의 Self-Localization)

  • Sohn, Eun-Ho;Kwon, Bang-Hyun;Kim, Young-Chul;Chong, Kil-To
    • Proceedings of the KIEE Conference
    • /
    • /
    • pp.318-320
    • /
    • 2006
  • Inaccurate localization exposes a robot to many dangerous conditions. It could make a robot be moved to wrong direction or damaged by collision with surrounding obstacles. There are numerous approaches to self-localization, and there are different modalities as well (vision, laser range finders, ultrasonic sonars). Since sensor information is generally uncertain and contains noise, there are many researches to reduce the noise. But, the correctness is limited because most researches are based on statistical approach. The goal of our research is to measure more exact robot location by matching between built VRML 3D model and real vision image. To determine the position of mobile robot, landmark-localitzation technique has been applied. Landmarks are any detectable structure in the physical environment. Some use vertical lines, others use specially designed markers, In this paper, specially designed markers are used as landmarks. Given known focal length and a single image of three landmarks it is possible to compute the angular separation between the lines of sight of the landmarks. The image-processing and neural network pattern matching techniques are employed to recognize landmarks placed in a robot working environment. After self-localization, the 2D scene of the vision is overlaid with the VRML scene.

  • PDF

Self-localization of a Mobile Robot for Decreasing the Error and VRML Image Overlay (오차 감소를 위한 이동로봇 Self-Localization과 VRML 영상오버레이 기법)

  • Kwon Bang-Hyun;Shon Eun-Ho;Kim Young-Chul;Chong Kil-To
    • Journal of Institute of Control, Robotics and Systems
    • /
    • v.12 no.4
    • /
    • pp.389-394
    • /
    • 2006
  • Inaccurate localization exposes a robot to many dangerous conditions. It could make a robot be moved to wrong direction or damaged by collision with surrounding obstacles. There are numerous approaches to self-localization, and there are different modalities as well (vision, laser range finders, ultrasonic sonars). Since sensor information is generally uncertain and contains noise, there are many researches to reduce the noise. But, the correctness is limited because most researches are based on statistical approach. The goal of our research is to measure more exact robot location by matching between built VRML 3D model and real vision image. To determine the position of mobile robot, landmark-localization technique has been applied. Landmarks are any detectable structure in the physical environment. Some use vertical lines, others use specially designed markers, In this paper, specially designed markers are used as landmarks. Given known focal length and a single image of three landmarks it is possible to compute the angular separation between the lines of sight of the landmarks. The image-processing and neural network pattern matching techniques are employed to recognize landmarks placed in a robot working environment. After self-localization, the 2D scene of the vision is overlaid with the VRML scene.

Self-Positioning of a Mobile Robot using a Vision System and Image Overlay with VRML (비전 시스템을 이용한 이동로봇 Self-positioning과 VRML과의 영상오버레이)

  • Hyun, Kwon-Bang;To, Chong-Kil
    • Proceedings of the KIEE Conference
    • /
    • /
    • pp.258-260
    • /
    • 2005
  • We describe a method for localizing a mobile robot in the working environment using a vision system and VRML. The robot identifies landmarks in the environment and carries out the self-positioning. The image-processing and neural network pattern matching technique are employed to recognize landmarks placed in a robot working environment. The robot self-positioning using vision system is based on the well-known localization algorithm. After self-positioning, 2D scene is overlaid with VRML scene. This paper describes how to realize the self-positioning and shows the result of overlaying between 2D scene and VRML scene. In addition we describe the advantage expected from overlapping both scenes.

  • PDF

A Path tracking algorithm and a VRML image overlay method (VRML과 영상오버레이를 이용한 로봇의 경로추적)

  • Sohn, Eun-Ho;Zhang, Yuanliang;Kim, Young-Chul;Chong, Kil-To
    • Proceedings of the IEEK Conference
    • /
    • /
    • pp.907-908
    • /
    • 2006
  • We describe a method for localizing a mobile robot in its working environment using a vision system and Virtual Reality Modeling Language (VRML). The robot identifies landmarks in the environment, using image processing and neural network pattern matching techniques, and then its performs self-positioning with a vision system based on a well-known localization algorithm. After the self-positioning procedure, the 2-D scene of the vision is overlaid with the VRML scene. This paper describes how to realize the self-positioning, and shows the overlap between the 2-D and VRML scenes. The method successfully defines a robot's path.

  • PDF

Path finding via VRML and VISION overlay for Autonomous Robotic (로봇의 위치보정을 통한 경로계획)

  • Sohn, Eun-Ho;Park, Jong-Ho;Kim, Young-Chul;Chong, Kil-To
    • Proceedings of the KIEE Conference
    • /
    • /
    • pp.527-529
    • /
    • 2006
  • In this paper, we find a robot's path using a Virtual Reality Modeling Language and overlay vision. For correct robot's path we describe a method for localizing a mobile robot in its working environment using a vision system and VRML. The robt identifies landmarks in the environment, using image processing and neural network pattern matching techniques, and then its performs self-positioning with a vision system based on a well-known localization algorithm. After the self-positioning procedure, the 2-D scene of the vision is overlaid with the VRML scene. This paper describes how to realize the self-positioning, and shows the overlap between the 2-D and VRML scenes. The method successfully defines a robot's path.

  • PDF