• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• 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.

• 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.

• 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.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.515-522
• /
• 2021

It is hard to prepare sufficient training data for speech emotion recognition due to the difficulty of emotion labeling. In this paper, we apply transfer learning with large-scale training data for speech recognition on a transformer-based model to improve the performance of speech emotion recognition. In addition, we propose a method to utilize context information without decoding by multi-task learning with speech recognition. According to the speech emotion recognition experiments using the IEMOCAP dataset, our model achieves a weighted accuracy of 70.6 % and an unweighted accuracy of 71.6 %, which shows that the proposed method is effective in improving the performance of speech emotion recognition.

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.387-396
• /
• 2020

Wearable biosensors have the potential to non-invasively and continuously monitor seniors' stress in their daily interaction with the urban environment, thereby enabling to address the stress and ultimately advance their outdoor mobility. However, current wearable biosensor-based stress detection methods have several drawbacks in field application due to their dependence on batch-learning algorithms. First, these methods train a single classifier, which might not account for multiple subjects' different physiological reactivity to stress. Second, they require a great deal of computational power to store and reuse all previous data for updating the signle classifier. To address this issue, we tested the feasibility of online multi-task learning (OMTL) algorithms to identify multiple seniors' stress from electrodermal activity (EDA) collected by a wristband-type biosensor in a daily trip setting. As a result, OMTL algorithms showed the higher test accuracy (75.7%, 76.2%, and 71.2%) than a batch-learning algorithm (64.8%). This finding demonstrates that the OMTL algorithms can strengthen the field applicability of the wearable biosensor-based stress detection, thereby contributing to better understanding the seniors' stress in the urban environment and ultimately advancing their mobility.

• 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.

• 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.

• Journal of Korea Multimedia Society
• /
• v.22 no.10
• /
• pp.1149-1159
• /
• 2019

We present a novel deep learning architecture for obtaining a latent image from a single blurry image, which contains dynamic motion blurs through object/camera movements. The proposed architecture consists of two sub-modules: blur image restoration and optical flow estimation. The tasks are highly related in that object/camera movements make cause blurry artifacts, whereas they are estimated through optical flow. The ablation study demonstrates that training multi-task architecture simultaneously improves both tasks compared to handling them separately. Objective and subjective evaluations show that our method outperforms the state-of-the-arts deep learning based techniques.

• The Journal of Korean society of community based occupational therapy
• /
• v.8 no.2
• /
• pp.1-14
• /
• 2018

Objective : The purpose of this study was to investigate the change in self-efficacy and writing ability after applying a Task-Oriented Multi-Sensory Movement Program to children with ADHD tendency accompanied by learning delays. Methods : A Task-Oriented Multi-Sensory Movement Program was implemented to children with ADHD tendency accompanied by learning delays attending S elementary school. The research proceeded in the order of a pre-test, Task-Oriented Multi-Sensory Movement intervention, and a post-test. The first session involved a pre-test, in which the children's self-efficacy and writing ability were examined using self-efficacy test and type 'A' KNISE-BAAT writing test. The multisensory group activity program intervention was conducted for a total of 8 sessions. In the last session, a post-test was conducted using self-efficacy test and type 'B' KNISE-BAAT writing test. Data collected from the tests were analyzed using SPSS Statistics 18. Results : According to the tests taken before and after implementing the Task-Oriented Multi-Sensory Movement Program, there was a significant improvement in self-efficacy (school, society), writing ability(command of vocabulary and sentence). Conclusion : Task-Oriented Multi-Sensory Movement Program may be used as a beneficial measure to improve the self-efficacy and writing abilities of children with ADHD tendency accompanied by learning delays. It is necessary to design various intervention models by combining educational media based on a multisensory approach.

• ETRI Journal
• /
• v.43 no.6
• /
• pp.1004-1012
• /
• 2021

The collaboration productively interacting between multi-agents has become an emerging issue in real-world applications. In reinforcement learning, multi-agent environments present challenges beyond tractable issues in single-agent settings. This collaborative environment has the following highly complex attributes: sparse rewards for task completion, limited communications between each other, and only partial observations. In particular, adjustments in an agent's action policy result in a nonstationary environment from the other agent's perspective, which causes high variance in the learned policies and prevents the direct use of reinforcement learning approaches. Unexpected social loafing caused by high dispersion makes it difficult for all agents to succeed in collaborative tasks. Therefore, we address a paradox caused by the social loafing to significantly reduce total returns after a certain timestep of multi-agent reinforcement learning. We further demonstrate that the collaborative paradox in multi-agent environments can be avoided by our proposed effective early stop method leveraging a metric for social loafing.