Graph-based NLP
From Language and Information Technologies
Jump to: navigation, search
The goal of this research project is to investigate efficient graph-based representations of text, and explore the application of ranking models based on such graph structures to natural language processing tasks. We bring together methods from computational linguistics and graph-theory, and combine them into a suite of innovative approaches that will improve and ultimately solve difficult problems in natural language processing. Specifically, we are currently working on the application of graph centrality algorithms to problems such as word sense disambiguation, text summarization and keyword extraction.
So, a while ago, I’ve decided to code a library to plot some information I had. The idea was to create simple graphics in a way they would be easy to create, beautiful and good to present to people with no or few backgrounds on math and computers.
Graph mining refers to extracting knowledge from massive graphs. The data sets of telephone calls we see at AT&T can be viewed as a single graph, with several hundred million phone numbers as nodes, and calls between phone numbers as edges. It is a giant social network, like an internet connections graph or a rich citation network.
I. Hubner, E. Deeds, and E. Shakhnovich. PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 103 (47):
17747-17752(November 2006)
W. Bielecki, T. Klimek, and K. Trifunovic. Electronic Notes in Discrete Mathematics, (2009)International Conference on Graph Theory and its Applications.