Neural Nets for NLP - Recurrent Networks for Sentence or Language Modeling

Neural Nets for NLP - Recurrent Networks for Sentence or Language Modeling

Graham Neubig via YouTube Direct link

Recurrent Neural Networks (Elman 1990)

9 of 18

9 of 18

Recurrent Neural Networks (Elman 1990)

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Neural Nets for NLP - Recurrent Networks for Sentence or Language Modeling

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Why Model Sentence Pairs?
  3. 3 Siamese Network (Bromley et al. 1993)
  4. 4 Convolutional Matching Model (Hu et al. 2014) • Concatenate sentences into a 30 tensor and perform convolution
  5. 5 Convolutional Features + Matrix-based Pooling in and Schutze 2015
  6. 6 NLP and Sequential Data
  7. 7 Long-distance Dependencies in Language
  8. 8 Can be Complicated!
  9. 9 Recurrent Neural Networks (Elman 1990)
  10. 10 Unrolling in Time • What does processing a sequence look like?
  11. 11 What Can RNNs Do?
  12. 12 Representing Sentences
  13. 13 e.g. Language Modeling
  14. 14 RNNLM Example: Loss Calculation and State Update
  15. 15 Vanishing Gradient • Gradients decrease as they get pushed back
  16. 16 LSTM Structure
  17. 17 What can LSTMs Learn? (2) (Shi et al. 2016, Radford et al. 2017) Count length of sentence
  18. 18 Handling Long Sequences

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.