Tree-structured models have been widely used for human pose estimation, in either 2D or 3D. While such models allow efficient learning and inference, they fail to capture additiona...
Jointly parsing two languages has been shown to improve accuracies on either or both sides. However, its search space is much bigger than the monolingual case, forcing existing ap...
We present the first unsupervised approach to the problem of learning a semantic parser, using Markov logic. Our USP system transforms dependency trees into quasi-logical forms, r...
Stochastic dependency parsers can achieve very good results when they are trained on large corpora that have been manually annotated. Active learning is a procedure that aims at r...
In practical applications, decoding speed is very important. Modern structured learning technique adopts template based method to extract millions of features. Complicated templat...