Learning Grammars for Architecture-Specific Facade Parsing

DeepFacade: A Deep Learning Approach to Facade Parsing

The parsing of building facades is a key component to the problem of 3D street scenes reconstruction, which is long desired in computer vision. In this paper, we propose a deep learning based method for segmenting a facade into semantic categories. Man-made structures often present the characteristic of symmetry. Based on this observation, we propose a symmetric regularizer for training the neu...

A Parallel Parsing VLSI Architecture for Arbitrary Context Free Grammars

In this paper we propose a fixed size one-dimensional VLSI architecture for the parallel parsing of arbitrary context free (CF) grammars, based on Earley’s algorithm. The algorithm is transformed into an equivalent double nested loop with loopcarried dependencies. We first map the algorithm into a 1-D array with unbounded number of cells. The time complexity of this architecture is O(n), which ...

Learning and Parsing Stochastic Unification-Based Grammars

Stochastic Unification-Based Grammars combine knowledgerich and data-rich approaches to natural language processing. This provides a rich structure to the learning and parsing (decoding) tasks that can be described with undirected graphical models. While most work to date has treated parsing as a straight-forward multi-class classification problem, we are beginning to see how this structure can...

Learning Synchronous Grammars for Semantic Parsing with Lambda Calculus

This paper presents the first empirical results to our knowledge on learning synchronous grammars that generate logical forms. Using statistical machine translation techniques, a semantic parser based on a synchronous context-free grammar augmented with λoperators is learned given a set of training sentences and their correct logical forms. The resulting parser is shown to be the bestperforming...

Learning Grammars for Different Parsing Tasks by Partition Search