2002 ACritiqueandImprovementofAnEval

(Pevzner & Hearst, 2002) ⇒ Lev Pevzner, and Marti A. Hearst. (2002). “A Critique and Improvement of An Evaluation Metric for Text Segmentation.” In: Computational Linguistics, 28(1). doi:10.1162/089120102317341756

Subject Headings: Window Diff, Pk Metric.

Notes

Cited By

http://scholar.google.com/scholar?q=%222002%22+A+Critique+and+Improvement+of+An+Evaluation+Metric+for+Text+Segmentation

Quotes

Abstract

The Pk evaluation metric, initially proposed by Beeferman, Berger, and Lafferty (1997), is becoming the standard measure for assessing text segmentation algorithms. However, a theoretical analysis of the metric finds several problems: the metric penalizes false negatives more heavily than false positives, overpenalizes near misses, and is affected by variation in segment size distribution. We propose a simple modification to the Pk metric that remedies these problems. This new metric — called Window Diff — moves a fixed-sized window across the text and penalizes the algorithm whenever the number of boundaries within the window does not match the true number of boundaries for that window of text.

References

;

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2002 ACritiqueandImprovementofAnEval	Marti Hearst Lev Pevzner			A Critique and Improvement of An Evaluation Metric for Text Segmentation				10.1162/089120102317341756		2002