Neural Nets for NLP 2017 - Convolutional Networks for Text

Neural Nets for NLP 2017 - Convolutional Networks for Text

Graham Neubig via YouTube Direct link

A First Try: Bag of Words (BOW)

3 of 17

3 of 17

A First Try: Bag of Words (BOW)

Class Central Classrooms beta

YouTube playlists curated by Class Central.

Classroom Contents

Neural Nets for NLP 2017 - Convolutional Networks for Text

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

  1. 1 Intro
  2. 2 An Example Prediction Problem: Sentence Classification
  3. 3 A First Try: Bag of Words (BOW)
  4. 4 Continuous Bag of Words (CBOW) movie
  5. 5 What do Our Vectors Represent?
  6. 6 Why Bag of n-grams?
  7. 7 What Problems w/ Bag of n-grams?
  8. 8 Time Delay Neural Networks (Waibel et al. 1989)
  9. 9 Convolutional Networks (LeCun et al. 1997)
  10. 10 Standard conv2d Function
  11. 11 Stacked Convolution
  12. 12 Dilated Convolution (e.g. Kalchbrenner et al. 2016)
  13. 13 An Aside: Nonlinear Functions • Proper choice of a non-linear function is essential in stacked networks
  14. 14 Why (Dilated) Convolution for Modeling Sentences? • In contrast to recurrent neural networks (next class)
  15. 15 Example: Dependency Structure
  16. 16 Why Model Sentence Pairs?
  17. 17 Siamese Network (Bromley et al. 1993)

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.