Papers by Pierre-Emmanuel Mazare
Learning from Dialogue after Deployment: Feed Yourself, Chatbot! (P19-1)
Copied to clipboard
| Challenge: | a majority of conversations a dialogue agent sees over its lifetime occur after it has already been trained and deployed, leaving a vast store of potential training signal untapped. |
| Approach: | They propose a self-feeding chatbot that extracts new training examples from conversations it participates in. |
| Outcome: | The proposed chatbot extracts training examples from conversations it participates in and predicts user satisfaction in its responses. |