Hyperbolic Dependency Tree Visualization for Parser Evaluation

Le Wang, Yue Zhang, Lei Shi

Abstract: We present a novel tool to visualize dependency trees in a hyperbolic layout, and to provide visual support for comparative evaluation of parsing errors. Compared with traditional flat tree visualization, our hyperbolic tree visualization tool can be more convenient for showing long-range dependencies. Our tool integrates the hyperbolic view with a flat view, and support corpus-level error analysis. It offers several features, including statistical analysis of error distributions, visual analysis of individual dependency trees, and an integrated online interface.