Neural Nets for NLP 2020 - Machine Reading with Neural Nets

Neural Nets for NLP 2020 - Machine Reading with Neural Nets

Graham Neubig via YouTube Direct link

Intro

1 of 30

1 of 30

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Neural Nets for NLP 2020 - Machine Reading with Neural Nets

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

  1. 1 Intro
  2. 2 What is Machine Reading?
  3. 3 Machine Reading Question Answering Formats
  4. 4 Multiple-choice Question Tasks
  5. 5 Span Selection
  6. 6 Cloze Questions
  7. 7 What is Necessary for Machine Reading?
  8. 8 All Datasets Have Their Biases
  9. 9 A Case Study: bAbl (Weston et al. 2014)
  10. 10 An Examination of CNN/ Daily Mail (Chen et al. 2015)
  11. 11 Adversarial Examples in Machine Reading (Jia and Liang 2017)
  12. 12 Adversarial Creation of New Datasets? (Zellers et al. 2018)
  13. 13 Natural Questions Kwiatkowski et al. 2019
  14. 14 A Basic Model for Document Attention
  15. 15 A First Try: Attentive Reader
  16. 16 Attention-over-attention
  17. 17 Bidirectional Attention Flow
  18. 18 Word Classification vs. Span Classification
  19. 19 Dynamic Span Decoder (Xiong et al. 2017)
  20. 20 Multi-step Reasoning Datasets
  21. 21 Softened, and Multi-layer Memory Networks (Sukhbaatar et al. 2015) • Use standard softmax attention, and multiple layers
  22. 22 When to Stop Reasoning?
  23. 23 Coarse-to-fine Question Answering (Choi et al. 2017)
  24. 24 Retrieval + Language Model
  25. 25 Explicit Question Decomposition for Multi-step Reasoning
  26. 26 Question Answering with Context (Choi et al. 2018, Reddy et al. 2018)
  27. 27 An Aside: Traditional Computational Semantics • Reasoning is something that traditional semantic representations are really good at!
  28. 28 Numerical Calculation
  29. 29 Machine Reading with Symbolic Operations . Can we explicitly incorporate numerical reasoning in machine reading?
  30. 30 Solving Word Problems w/ Symbolic Reasoning • Idea: combine semantic parsing (with explicit functions) and machine reading

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.