Discriminative reranking has been able to significantly improve parsing performance, and co-training has proven to be an effective weakly supervised learning algorithm to bootstr...
Conventional n-best reranking techniques often suffer from the limited scope of the nbest list, which rules out many potentially good alternatives. We instead propose forest reran...
The paper describes a system which uses packed parser output directly to build semantic representations. More specifically, the system takes as input Packed Shared Forests in the ...
Language and image understanding are two major goals of artificial intelligence which can both be conceptually formulated in terms of parsing the input signal into a hierarchical ...
Leo Zhu, Yuanhao Chen, Yuan Lin, Chenxi Lin, Alan ...
The objective of this paper is to parse object trajectories in surveillance video against occlusion, interruption, and background clutter. We present a spatio-temporal graph (ST-G...