Neural Nets for NLP 2017 - Models of Dialog

Neural Nets for NLP 2017 - Models of Dialog

Graham Neubig via YouTube Direct link

Intro

1 of 22

1 of 22

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Neural Nets for NLP 2017 - Models of Dialog

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

  1. 1 Intro
  2. 2 Types of Dialog
  3. 3 Two Paradigms
  4. 4 Generation-based Models (Ritter et al. 2011)
  5. 5 Neural Models for Dialog Response Generation
  6. 6 Hierarchical Encoder- decoder Model (Serban et al. 2016)
  7. 7 Dialog allows Much More Varied Responses
  8. 8 Diversity Promoting Objective for Conversation (Li et al. 2016)
  9. 9 Diversity is a Problem for Evaluation!
  10. 10 Using Multiple References with Human Evaluation Scores (Gallay et al. 2015)
  11. 11 Learning to Evaluate • Use context, true response, and actual response to learn a regressor that predicts goodness (Lowe et al. 2017) • Important similar to model, but has access to reference
  12. 12 Problem 3: Dialog Agents should have Personality
  13. 13 Personality Infused Dialog (Mairesse et al. 2007)
  14. 14 Persona-based Neural Dialog Model (Li et al. 2017)
  15. 15 Dialog Response Retrieval
  16. 16 Retrieval-based Chat (Lee et al. 2009)
  17. 17 Neural Response Retrieval (Nio et al. 2014)
  18. 18 Smart Reply for Email Retrieval (Kannan et al. 2016)
  19. 19 Traditional Task-completion Dialog Framework
  20. 20 NLU (for Slot Filling) w/ Neural Nets (Mesnil et al. 2015)
  21. 21 Dialog State Tracking
  22. 22 Language Generation from Dialog State w/ Neural Nets (Wen et al. 2015)

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.