CMU Multilingual NLP 2020 - Advanced Text Classification-Labeling

CMU Multilingual NLP 2020 - Advanced Text Classification-Labeling

Graham Neubig via YouTube Direct link

Intro

1 of 24

1 of 24

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

CMU Multilingual NLP 2020 - Advanced Text Classification-Labeling

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

  1. 1 Intro
  2. 2 Text Classification
  3. 3 Sequence Labeling Given an input text X, predict an output label sequence of equal length
  4. 4 Reminder: Bi-RNNS - Simple and standard model for sequence labeling for classification
  5. 5 Issues w/ Simple BiRNN
  6. 6 Alternative: Bag of n-grams
  7. 7 Unknown Words
  8. 8 Sub-word Segmentation
  9. 9 Unsupervised Subword Segmentation Algorithms
  10. 10 Sub-word Based Embeddings
  11. 11 Sub-word Based Embedding Models
  12. 12 Embeddings for Cross-lingual Learning: Soft Decoupled Encoding
  13. 13 Labeled/Unlabeled Data Problem: we have very little labeled data for most analysis tasks for most languages
  14. 14 Joint Multi-task Learning
  15. 15 Pre-training
  16. 16 Masked Language Modeling
  17. 17 Thinking about Multi-tasking, and Pre-trained Representations
  18. 18 Other Monolingual BERTS
  19. 19 XTREME: Comparing Multilingual Representations
  20. 20 Why Call it "Structured" Prediction?
  21. 21 Why Model Interactions in Output?
  22. 22 Local Normalization vs. Global Normalization
  23. 23 Potential Functions
  24. 24 Discussion

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.