• Title, Summary, Keyword: Multi-hot 벡터

Search Result 2, Processing Time 0.022 seconds

Sequence-to-sequence Autoencoder based Korean Text Error Correction using Syllable-level Multi-hot Vector Representation (음절 단위 Multi-hot 벡터 표현을 활용한 Sequence-to-sequence Autoencoder 기반 한글 오류 보정기)

  • Song, Chisung;Han, Myungsoo;Cho, Hoonyoung;Lee, Kyong-Nim
    • Annual Conference on Human and Language Technology
    • /
    • /
    • pp.661-664
    • /
    • 2018
  • 온라인 게시판 글과 채팅창에서 주고받는 대화는 실제 사용되고 있는 구어체 특성이 잘 반영된 텍스트 코퍼스로 음성인식의 언어 모델 재료로 활용하기 좋은 학습 데이터이다. 하지만 온라인 특성상 노이즈가 많이 포함되어 있기 때문에 학습에 직접 활용하기가 어렵다. 본 논문에서는 사용자 입력오류가 다수 포함된 문장에서의 한글 오류 보정을 위한 sequence-to-sequence Denoising Autoencoder 모델을 제안한다.

  • PDF

Variation for Mental Health of Children of Marginalized Classes through Exercise Therapy using Deep Learning (딥러닝을 이용한 소외계층 아동의 스포츠 재활치료를 통한 정신 건강에 대한 변화)

  • Kim, Myung-Mi
    • The Journal of the Korea institute of electronic communication sciences
    • /
    • v.15 no.4
    • /
    • pp.725-732
    • /
    • 2020
  • This paper uses variables following as : to follow me well(0-9), it takes a lot of time to make a decision (0-9), lethargy(0-9) during physical activity in the exercise learning program of the children in the marginalized class. This paper classifies 'gender', 'physical education classroom', and 'upper, middle and lower' of age, and observe changes in ego-resiliency and self-control through sports rehabilitation therapy to find out changes in mental health. To achieve this, the data acquired was merged and the characteristics of large and small numbers were removed using the Label encoder and One-hot encoding. Then, to evaluate the performance by applying each algorithm of MLP, SVM, Dicesion tree, RNN, and LSTM, the train and test data were divided by 75% and 25%, and then the algorithm was learned with train data and the accuracy of the algorithm was measured with the Test data. As a result of the measurement, LSTM was the most effective in sex, MLP and LSTM in physical education classroom, and SVM was the most effective in age.