JoBimViz: A Web-based Visualization for Graph-based Distributional Semantic Models

This paper introduces a web-based visualization framework for graph-based distributional semantic models. The visualization supports a wide range of data structures, including term similarities, similarities of contexts, support of multiword expressions, sense clusters for terms and sense labels. In contrast to other browsers of semantic resources, our visualization accepts input sentences, which are subsequently processed with languageindependent or language-dependent ways to compute term-context representations. Our web demonstrator currently contains models for multiple languages, based on different preprocessing such as dependency parsing and n-gram context representations. These models can be accessed from a database, the web interface and via a RESTful API. The latter facilitates the quick integration of such models in research prototypes.

• Type: Journal
• Year: 2015
• Where: ACL
• Authors: Eugen Ruppert, Manuel Kaufmann, Martin Riedl 0002, Chris Biemann
• Keywords: ACL 2015, Computational Linguistics