Details

Autor(en) / Beteiligte

• Pevzner, Lev
• Hearst, Marti A.

Titel

A Critique and Improvement of an Evaluation Metric for Text Segmentation

Ist Teil von

• Computational linguistics - Association for Computational Linguistics, 2002-03, Vol.28 (1), p.19-36

Ort / Verlag

One Rogers Street, Cambridge, MA 02142-1209, USA: MIT Press

Erscheinungsjahr

2002

Link zum Volltext

Quelle

ACM Digital Library

Beschreibungen/Notizen

• The P 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 P 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.