Now showing items 1-2 of 2
Reinforcement Learning for Mapping Instructions to Actions
(Association for Computational Linguistics, 2009-08)
In this paper, we present a reinforcement learning approach for mapping natural language instructions to sequences of executable actions. We assume access to a reward function that defines the quality of the executed ...
Global models of document structure using latent permutations
(Association for Computational Linguistics, 2009-06)
We present a novel Bayesian topic model for learning discourse-level document structure. Our model leverages insights from discourse theory to constrain latent topic assignments in a way that reflects the underlying ...