Publication
EMNLP 2013
Conference paper

JobimText visualizer: A Graph-based Approach to Contextualizing Distributional Similarity

Download paper

Abstract

We introduce an interactive visualization component for the JoBimText project. JoBimText is an open source platform for large-scale distributional semantics based on graph representations. First we describe the underlying technology for computing a distributional thesaurus on words using bipartite graphs of words and context features, and contextualizing the list of semantically similar words towards a given sentential context using graph-based ranking. Then we demonstrate the capabilities of this contextualized text expansion technology in an interactive visualization. The visualization can be used as a semantic parser providing contextualized expansions of words in text as well as disambiguation to word senses induced by graph clustering, and is provided as an open source tool.

Date

18 Oct 2013

Publication

EMNLP 2013

Authors

Tags

Resources

Share