Cluster Labelling based on Concepts in a Machine-Readable Dictionary
Fumiyo Fukumoto, Yoshimi Suzuki · International Joint Conference on Natural Language Processing · 2011
This paper addresses the issue of cluster labeling and presents a method for assigning labels by using concepts in a machinereadable dictionary. We assume that salient terms in the cluster content have the same hypernym because hypernymic semantic relation represents a generalization that goes from specific to generic. Our experimental results reveal that hypernymic semantic relations can be exploited to increase labeling accuracy, as the results of 0.441 F-score improves over the two baselines.