We present three systems for surface natural language generation that are trainable from annotated corpora. The first two systems, called NLG1 and NLG2, require a corpus marked on...
Systems based on statistical and machine learning methods have been shown to be extremely effective and scalable for the analysis of large amount of textual data. However, in the r...
Organizations today collect and store large amounts of data in various formats and locations. However they are sometimes required to locate all instances of a certain type of data....
We propose a non-parametric Bayesian model for unsupervised semantic parsing. Following Poon and Domingos (2009), we consider a semantic parsing setting where the goal is to (1) d...
We study the challenging problem of localizing and classifying category-specific object contours in real world images. For this purpose, we present a simple yet effective method ...
Bharath Hariharan, Pablo Arbelaez, Lubomir Bourdev...