Majority of the existing approaches to service composition, including the widely popular planning based techniques, are not able to automatically compose practical workflows that ...
We describe a new method for learning the conditional probability distribution of a binary-valued variable from labelled training examples. Our proposed Compositional Noisy-Logica...
Abstract. We describe a new method for unsupervised structure learning of a hierarchical compositional model (HCM) for deformable objects. The learning is unsupervised in the sense...
Long Zhu, Chenxi Lin, Haoda Huang, Yuanhao Chen, A...
We describe a methodology for creating composite web services, a key ingredient in spatial data infrastructure (SDI) applications, which we demonstrate on an emergency management ...
Compositional question answering begins by mapping questions to logical forms, but training a semantic parser to perform this mapping typically requires the costly annotation of t...