• Title, Summary, Keyword: multi-task learning

Search Result 60, Processing Time 0.03 seconds

Exploring the Relationship between Shared Space and Performance in Multi-Task Learning (Multi-Task Learning에서 공유 공간과 성능과의 관계 탐구)

  • Seong, Su-Jin;Park, Seong-Jae;Jeong, In-Gyu;Cha, Jeong-Won
    • Annual Conference on Human and Language Technology
    • /
    • /
    • pp.305-309
    • /
    • 2018
  • 딥러닝에서 층을 공유하여 작업에 따라 변하지 않는 정보를 사용하는 multi-task learning이 다양한 자연어 처리 문제에 훌륭하게 사용되었다. 그렇지만 우리가 아는 한 공유 공간의 상태와 성능과의 관계를 조사한 연구는 없었다. 본 연구에서는 공유 공간과 task 의존 공간의 자질의 수와 오염 정도가 성능에 미치는 영향도 조사하여 공유 공간과 성능 관계에 대해서 탐구한다. 이 결과는 multi-task를 진행하는 실험에서 공유 공간의 역할과 성능의 관계를 밝혀서 시스템의 성능 향상에 도움이 될 것이다.

  • PDF

Facial Action Unit Detection with Multilayer Fused Multi-Task and Multi-Label Deep Learning Network

  • He, Jun;Li, Dongliang;Bo, Sun;Yu, Lejun
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.13 no.11
    • /
    • pp.5546-5559
    • /
    • 2019
  • Facial action units (AUs) have recently drawn increased attention because they can be used to recognize facial expressions. A variety of methods have been designed for frontal-view AU detection, but few have been able to handle multi-view face images. In this paper we propose a method for multi-view facial AU detection using a fused multilayer, multi-task, and multi-label deep learning network. The network can complete two tasks: AU detection and facial view detection. AU detection is a multi-label problem and facial view detection is a single-label problem. A residual network and multilayer fusion are applied to obtain more representative features. Our method is effective and performs well. The F1 score on FERA 2017 is 13.1% higher than the baseline. The facial view recognition accuracy is 0.991. This shows that our multi-task, multi-label model could achieve good performance on the two tasks.

Korean Dependency Parsing using Pointer Networks (포인터 네트워크를 이용한 한국어 의존 구문 분석)

  • Park, Cheoneum;Lee, Changki
    • Journal of KIISE
    • /
    • v.44 no.8
    • /
    • pp.822-831
    • /
    • 2017
  • In this paper, we propose a Korean dependency parsing model using multi-task learning based pointer networks. Multi-task learning is a method that can be used to improve the performance by learning two or more problems at the same time. In this paper, we perform dependency parsing by using pointer networks based on this method and simultaneously obtaining the dependency relation and dependency label information of the words. We define five input criteria to perform pointer networks based on multi-task learning of morpheme in dependency parsing of a word. We apply a fine-tuning method to further improve the performance of the dependency parsing proposed in this paper. The results of our experiment show that the proposed model has better UAS 91.79% and LAS 89.48% than conventional Korean dependency parsing.

A model of the learning materials for the middle school multi-purpose English classes through TBL framework (과업 중심 학습방법에 기초한 중학교 영어교과 재량활동 학습자료 모형)

  • Lee, Jeong-Won;Lee, Kyeong-Ja
    • English Language & Literature Teaching
    • /
    • v.11 no.4
    • /
    • pp.335-363
    • /
    • 2005
  • One of the most important features in the 7th National Curriculum of English is the introduction of the middle school multi-purpose English classes. Despite the importance of the classes, there doesn't seem to be enough studies of developing learning materials for them. The purpose of the current study is, therefore, to develop English learning materials for the multi-purpose English classes based on the Task-Based Learning framework. To do so, various tasks were collected and adapted for the classes, and different teaching techniques suitable for the tasks were designed. It is hoped that this research will help teachers prepare for teaching materials for the classes, and students recognize their interests in English and to improve their English abilities.

  • PDF

Korean morphological analysis and phrase structure parsing using multi-task sequence-to-sequence learning (Multi-task sequence-to-sequence learning을 이용한 한국어 형태소 분석과 구구조 구문 분석)

  • Hwang, Hyunsun;Lee, Changki
    • Annual Conference on Human and Language Technology
    • /
    • /
    • pp.103-107
    • /
    • 2017
  • 한국어 형태소 분석 및 구구조 구문 분석은 한국어 자연어처리에서 난이도가 높은 작업들로서 최근에는 해당 문제들을 출력열 생성 문제로 바꾸어 sequence-to-sequence 모델을 이용한 end-to-end 방식의 접근법들이 연구되었다. 한국어 형태소 분석 및 구구조 구문 분석을 출력열 생성 문제로 바꿀 시 해당 출력 결과는 하나의 열로서 합쳐질 수가 있다. 본 논문에서는 sequence-to-sequence 모델을 이용하여 한국어 형태소 분석 및 구구조 구문 분석을 동시에 처리하는 모델을 제안한다. 실험 결과 한국어 형태소 분석과 구구조 구문 분석을 동시에 처리할 시 형태소 분석이 구구조 구문 분석에 영향을 주는 것을 확인 하였으며, 구구조 구문 분석 또한 형태소 분석에 영향을 주어 서로 영향을 줄 수 있음을 확인하였다.

  • PDF

Korean morphological analysis and phrase structure parsing using multi-task sequence-to-sequence learning (Multi-task sequence-to-sequence learning을 이용한 한국어 형태소 분석과 구구조 구문 분석)

  • Hwang, Hyunsun;Lee, Changki
    • 한국어정보학회:학술대회논문집
    • /
    • /
    • pp.103-107
    • /
    • 2017
  • 한국어 형태소 분석 및 구구조 구문 분석은 한국어 자연어처리에서 난이도가 높은 작업들로서 최근에는 해당 문제들을 출력열 생성 문제로 바꾸어 sequence-to-sequence 모델을 이용한 end-to-end 방식의 접근법들이 연구되었다. 한국어 형태소 분석 및 구구조 구문 분석을 출력열 생성 문제로 바꿀 시 해당 출력 결과는 하나의 열로서 합쳐질 수가 있다. 본 논문에서는 sequence-to-sequence 모델을 이용하여 한국어 형태소 분석 및 구구조 구문 분석을 동시에 처리하는 모델을 제안한다. 실험 결과 한국어 형태소 분석과 구구조 구문 분석을 동시에 처리할 시 형태소 분석이 구구조 구문 분석에 영향을 주는 것을 확인 하였으며, 구구조 구문 분석 또한 형태소 분석에 영향을 주어 서로 영향을 줄 수 있음을 확인하였다.

  • PDF

Human Action Recognition Using Pyramid Histograms of Oriented Gradients and Collaborative Multi-task Learning

  • Gao, Zan;Zhang, Hua;Liu, An-An;Xue, Yan-Bing;Xu, Guang-Ping
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.8 no.2
    • /
    • pp.483-503
    • /
    • 2014
  • In this paper, human action recognition using pyramid histograms of oriented gradients and collaborative multi-task learning is proposed. First, we accumulate global activities and construct motion history image (MHI) for both RGB and depth channels respectively to encode the dynamics of one action in different modalities, and then different action descriptors are extracted from depth and RGB MHI to represent global textual and structural characteristics of these actions. Specially, average value in hierarchical block, GIST and pyramid histograms of oriented gradients descriptors are employed to represent human motion. To demonstrate the superiority of the proposed method, we evaluate them by KNN, SVM with linear and RBF kernels, SRC and CRC models on DHA dataset, the well-known dataset for human action recognition. Large scale experimental results show our descriptors are robust, stable and efficient, and outperform the state-of-the-art methods. In addition, we investigate the performance of our descriptors further by combining these descriptors on DHA dataset, and observe that the performances of combined descriptors are much better than just using only sole descriptor. With multimodal features, we also propose a collaborative multi-task learning method for model learning and inference based on transfer learning theory. The main contributions lie in four aspects: 1) the proposed encoding the scheme can filter the stationary part of human body and reduce noise interference; 2) different kind of features and models are assessed, and the neighbor gradients information and pyramid layers are very helpful for representing these actions; 3) The proposed model can fuse the features from different modalities regardless of the sensor types, the ranges of the value, and the dimensions of different features; 4) The latent common knowledge among different modalities can be discovered by transfer learning to boost the performance.

Effects of Multi-modal Guidance for the Acquisition of Sight Reading Skills: A Case Study with Simple Drum Sequences (멀티모달 가이던스가 독보 기능 습득에 미치는 영향: 드럼 타격 시퀀스에서의 사례 연구)

  • Lee, In;Choi, Seungmoon
    • The Journal of Korea Robotics Society
    • /
    • v.8 no.3
    • /
    • pp.217-227
    • /
    • 2013
  • We introduce a learning system for the sight reading of simple drum sequences. Sight reading is a cognitive-motor skill that requires reading of music symbols and actions of multiple limbs for playing the music. The system provides knowledge of results (KR) pertaining to the learner's performance by color-coding music symbols, and guides the learner by indicating the corresponding action for a given music symbol using additional auditory or vibrotactile cues. To evaluate the effects of KR and guidance cues, three learning methods were experimentally compared: KR only, KR with auditory cues, and KR with vibrotactile cues. The task was to play a random 16-note-long drum sequence displayed on a screen. Thirty university students learned the task using one of the learning methods in a between-subjects design. The experimental results did not show statistically significant differences between the methods in terms of task accuracy and completion time.

Deep Multi-task Network for Simultaneous Hazy Image Semantic Segmentation and Dehazing (안개영상의 의미론적 분할 및 안개제거를 위한 심층 멀티태스크 네트워크)

  • Song, Taeyong;Jang, Hyunsung;Ha, Namkoo;Yeon, Yoonmo;Kwon, Kuyong;Sohn, Kwanghoon
    • Journal of Korea Multimedia Society
    • /
    • v.22 no.9
    • /
    • pp.1000-1010
    • /
    • 2019
  • Image semantic segmentation and dehazing are key tasks in the computer vision. In recent years, researches in both tasks have achieved substantial improvements in performance with the development of Convolutional Neural Network (CNN). However, most of the previous works for semantic segmentation assume the images are captured in clear weather and show degraded performance under hazy images with low contrast and faded color. Meanwhile, dehazing aims to recover clear image given observed hazy image, which is an ill-posed problem and can be alleviated with additional information about the image. In this work, we propose a deep multi-task network for simultaneous semantic segmentation and dehazing. The proposed network takes single haze image as input and predicts dense semantic segmentation map and clear image. The visual information getting refined during the dehazing process can help the recognition task of semantic segmentation. On the other hand, semantic features obtained during the semantic segmentation process can provide cues for color priors for objects, which can help dehazing process. Experimental results demonstrate the effectiveness of the proposed multi-task approach, showing improved performance compared to the separate networks.

Performance Comparison Analysis on Named Entity Recognition system with Bi-LSTM based Multi-task Learning (다중작업학습 기법을 적용한 Bi-LSTM 개체명 인식 시스템 성능 비교 분석)

  • Kim, GyeongMin;Han, Seunggnyu;Oh, Dongsuk;Lim, HeuiSeok
    • Journal of Digital Convergence
    • /
    • v.17 no.12
    • /
    • pp.243-248
    • /
    • 2019
  • Multi-Task Learning(MTL) is a training method that trains a single neural network with multiple tasks influences each other. In this paper, we compare performance of MTL Named entity recognition(NER) model trained with Korean traditional culture corpus and other NER model. In training process, each Bi-LSTM layer of Part of speech tagging(POS-tagging) and NER are propagated from a Bi-LSTM layer to obtain the joint loss. As a result, the MTL based Bi-LSTM model shows 1.1%~4.6% performance improvement compared to single Bi-LSTM models.