Papers by Philip John Gorinski
Learning Dialog Policies from Weak Demonstrations (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods to train dialog managers struggle with large state spaces and sparse rewards. |
| Approach: | They propose a deep reinforcement learning algorithm that uses dialog data to guide the agent to successfully respond to a user's requests. |
| Outcome: | Experiments in a multi-domain dialog system framework validate our methods and get high success rates even when trained on out-of-domain data. |
What’s This Movie About? A Joint Neural Network Architecture for Movie Content Analysis (N18-1)
Copied to clipboard
| Challenge: | Using movie overviews, we can gain a general impression of a movie by summarizing its content, genre, and artistic style. |
| Approach: | They propose a novel end-to-end model that generates movie overviews from an online database and a multi-label encoder for identifying screenplay attributes. |
| Outcome: | The proposed model reliably assigns good labels for movie attributes and generates sentences conditioned on the identified attributes. |