Completed
Dialog More Dependent on Global Coherence
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Neural Nets for NLP 2018 - Models of Dialogue
Automatically move to the next video in the Classroom when playback concludes
- 1 Types of Dialog
- 2 Two Paradigms
- 3 Generation-based Models (Ritter et al. 2011)
- 4 Neural Models for Dialog Response Generation
- 5 Dialog More Dependent on Global Coherence
- 6 One Solution: Use Standard Architecture w/ More Context
- 7 Discourse-level VAE Model (Zhao et al. 2017)
- 8 Diversity Promoting Objective for Conversation (Li et al. 2016) • Basic idea we want responses that are likely given the context, unlikely otherwise • Method: subtract weighted unconditioned log prob…
- 9 Using Multiple References with Human Evaluation Scores (Gallay et al. 2015)
- 10 Learning to Evaluate • Use context, true response, and actual response to learn a regressor that predicts goodness (Lowe et al. 2017)
- 11 Problem 3: Dialog Agents should have Personality
- 12 Personality Infused Dialog (Mairesse et al. 2007)
- 13 Dialog Response Retrieval
- 14 Retrieval-based Chat (Lee et al. 2009)
- 15 Neural Response Retrieval (Nio et al. 2014)
- 16 Smart Reply for Email Retrieval (Kannan et al. 2016)
- 17 NLU (for Slot Filling) w/ Neural Nets (Mesnil et al. 2015)
- 18 Dialog State Tracking
- 19 Language Generation from Dialog State w/ Neural Nets (Won et al. 2015)
