Papers by Braden Hancock
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. |
Training Classifiers with Natural Language Explanations (P18-1)
Copied to clipboard
| Challenge: | a semantic parser converts explanations into programmatic labeling functions . a standard protocol for obtaining a labeled dataset provides only one bit of information per example . |
| Approach: | They propose a framework where an annotator provides an explanation for each labeling decision . they use a semantic parser to convert these explanations into programmatic labeling functions . |
| Outcome: | The proposed framework trains classifiers faster by providing explanations instead of labels . the proposed framework is based on a rule-based semantic parser . |