Normalized Entity Graph for Computing Local Coherence

Mohsen Mesgar, Michael Strube
2014 Proceedings of TextGraphs-9: the workshop on Graph-based Methods for Natural Language Processing  
Guinaudeau and Strube (2013) introduce a graph based model to compute local entity coherence. We propose a computationally efficient normalization method for these graphs and then evaluate it on three tasks: sentence ordering, summary coherence rating and readability assessment. In all tasks normalization improves the results.
doi:10.3115/v1/w14-3701 dblp:conf/textgraphs/Mesgar014 fatcat:geaxasvkprgifgz4gp7sf4uxv4