Spring 2017 CS292F Syllabus

• 04/04 Introduction, logistics, NLP, and deep learning.
• 04/06 Tips for a successful class project
• 04/11 Word embeddings
  • A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning, Collobert and Weston, ICML 2008
  • Glove: Global Vectors for Word Representation, J Pennington, R Socher, CD Manning - EMNLP, 2014
  • AutoExtend: Extending Word Embeddings to Embeddings for Synsets and Lexemes, Rothe and Schutze, ACL 2015
• 04/13 Knowledge base embeddings
  • A three-way model for collective learning on multi-relational data, M Nickel, V Tresp, HP Kriegel, ICML 2011
  • Translating embeddings for modeling multi-relational data, A Bordes, N Usunier, A Garcia-Duran, NIPS 2013
  • A Review of Relational Machine Learning for Knowledge Graphs, Nichel et al., Proceedings of the IEEE
• 04/18 Neural network basics (Project proposal due, HW1 out)
  • Learning representations by back-propagating errors, Nature, 1986
• 04/20 Recursive Neural Networks
  • Parsing with Compositional Vector Grammars, Socher et al., ACL 2013
  • Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank, Socher et al., EMNLP 2013
• 04/25 RNNs (NLP seminar: Stanford NLP's Jiwei Li 04/26)
  • Recurrent neural network based language model
  • Generating Sequences With Recurrent Neural Networks, Alex Graves, 2013 arxiv
• 04/27 LSTMs/GRUs
  • Long short term memory, S. Hochreiter and J. Schmidhuber, Neural Computation, 1997
  • On the Properties of Neural Machine Translation: Encoder–Decoder Approaches, Cho et al., 2014
• 05/02 Sequence-to-sequence models and neural machine translation (HW1 due and HW2 out)
  • Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation, Cho et al., EMNLP 2014
  • Sequence to Sequence Learning with Neural Networks, Sutskever et al., NIPS 2014
• 05/04 Attention mechanisms
  • NEURAL MACHINE TRANSLATION BY JOINTLY LEARNING TO ALIGN AND TRANSLATE, Bahdanau et al., ICLR 2015
  • Teaching Machines to Read and Comprehend, NIPS 2015
• 05/09 Project: mid-term presentation (1)
• 05/11 Project: mid-term presentation (2)
• 05/16 Convolutional Neural Networks (HW2 due)
  • Natural Language Processing (Almost) from Scratch, Collobert et al., JMLR 2011
  • A Sensitivity Analysis of (and Practitioners’ Guide to) Convolutional Neural Networks for Sentence Classification, Zhang and Wallace, Arxiv 2015
• 05/18 Language and vision
  • Show and Tell: A Neural Image Caption Generator, CVPR 2015
  • Deep Visual-Semantic Alignments for Generating Image Descriptions, Andrej Karpathy and Li Fei-Fei, CVPR 2015
• 05/23 Deep Reinforcement Learning 1
  • Deep Reinforcement Learning for Dialogue Generation, Li et al., EMNLP 2016
  • Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning, Narasimh et al., EMNLP 2016
• 05/25 Deep Reinforcement Learning 2
  • Playing Atari with Deep Reinforcement Learning, Mnih et al., NIPS workshop 2013
  • Continuous control with deep reinforcement learning, Lillicrap et al, ICLR 2016
• 05/30 Unsupervised Learning
  • Auto-encoding variational Bayes, Kingma and Welling, ICLR 2014
  • Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks, Redford et al., 2015
• 06/01 Project: final presentation (1)
• 06/06 Project: final presentation (2)
• 06/08 Project: final presentation (3)
• 06/10 23:59PM PT Project Final Report Due.