Lesson Open Access

Graph Clustering for Natural Language Processing

Ustalov, Dmitry

Graph-based representations are proven to be an effective approach for a variety of Natural Language Processing (NLP) tasks. Graph clustering makes it possible to extract useful knowledge by exploiting the implicit structure of the data. In this tutorial, we will present several efficient graph clustering algorithms, show their strengths and weaknesses as well as their implementations and applications. Then, the evaluation methodology in unsupervised NLP tasks will be discussed.

These materials are published under a CC BY-NC-SA license. Please feel welcome to share them! For viewer convenience, the slides published on ZENODO do not include interactive step-by-step examples.
Files (5.9 MB)
Name Size
GraphClustering.pdf
md5:c096a6daa97810ad4c5faa1c8f5a14e4
5.9 MB Download
228
176
views
downloads
All versions This version
Views 228228
Downloads 176176
Data volume 1.0 GB1.0 GB
Unique views 179179
Unique downloads 153153

Share

Cite as