Paper: Invited Talk: Learning from Rational Behavior

ACL ID D14-1078
Title Invited Talk: Learning from Rational Behavior
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2014

The ability to learn from user interactions can give systems access to unprecedented amounts of knowledge. This is evident in search engines, recommender systems, and electronic commerce, and it can be the key to solving other knowledge in- tensive tasks. However, extracting the knowledge conveyed by user interactions is less straightforward than standard ma- chine learning, since it requires learning systems that explicitly account for human decision making, human motivation, and human abilities. In this talk, I argue that the design space of such interactive learning systems encom- passes not only the machine learning algo- rithm itself, but also the design of the inter- action under an appropriate model of user behavior. To this effect, the talk explores how integrating microeconomic mo...