Search
Now showing items 1-3 of 3
Unsupervised multilingual grammar induction
(Association for Computational Linguistics, 2009-08)
We investigate the task of unsupervised constituency parsing from bilingual parallel corpora. Our goal is to use bilingual cues to learn improved parsing models for each language and to evaluate these models on held-out ...
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 ...
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 ...