janguck/deep_nlp_101

Natural Language Process with Deep Learning

과정개요

• 본 과정은 딥러닝을 활용하여 자연어 처리의 여러 방법들을 구현하는 방법에 대해 소개합니다

다루는 내용들

• Traditional approach for text represenstation
  • Bag of Word
  • TF-IDF
  • n-grams model
• Word Vector Representations
• Document Classification
• Documnet Simliarity

Reference

Word Vector Representations

• [NLM_2003] Bengio, Y., Ducharme, R., Vincent, P., & Jauvin, C. (2003). A neural probabilistic language model. Journal of machine learning research, 3(Feb), 1137-1155. Available - http://www.jmlr.org/papers/v3/bengio03a.html

Document Classification

• [CHAR_CNN_2015] Zhang, Xiang, Junbo Zhao, and Yann LeCun. "Character-level convolutional networks for text classification." In Advances in neural information processing systems, pp. 649-657. 2015. Aaailalble at: http://papers.nips.cc/paper/5782-character-level-convolutional-networks-fo
• [FASTTEXT_2016()]Joulin, Armand, Edouard Grave, Piotr Bojanowski, and Tomas Mikolov. "Bag of tricks for efficient text classification." arXiv preprint arXiv:1607.01759 (2016). Available at - https://arxiv.org/abs/1607.01759

Network Architecture

• [SEQ2SEQ_2014]Sutskever, Ilya, Oriol Vinyals, and Quoc V. Le. "Sequence to sequence learning with neural networks." In Advances in neural information processing systems, pp. 3104-3112. 2014. Available at - https://arxiv.org/abs/1409.3215

http://www.sciencedirect.com/science/article/pii/S0893608005001206