Timezone: »

On-the-Job Learning with Bayesian Decision Theory
Keenon Werling · Arun Tejasvi Chaganty · Percy Liang · Christopher Manning

Wed Dec 09 12:30 PM -- 01:00 PM (PST) @ Room 210 A

Our goal is to deploy a high-accuracy system starting with zero training examples. We consider an “on-the-job” setting, where as inputs arrive, we use real-time crowdsourcing to resolve uncertainty where needed and output our prediction when confident. As the model improves over time, the reliance on crowdsourcing queries decreases. We cast our setting as a stochastic game based on Bayesian decision theory, which allows us to balance latency, cost, and accuracy objectives in a principled way. Computing the optimal policy is intractable, so we develop an approximation based on Monte Carlo Tree Search. We tested our approach on three datasets-- named-entity recognition, sentiment classification, and image classification. On the NER task we obtained more than an order of magnitude reduction in cost compared to full human annotation, while boosting performance relative to the expert provided labels. We also achieve a 8% F1 improvement over having a single human label the whole set, and a 28% F1 improvement over online learning.

Author Information

Keenon Werling (Stanford University)
Arun Tejasvi Chaganty (Stanford)
Percy Liang (Stanford University)
Chris Manning (Stanford University)

More from the Same Authors