Automatic evaluation of information ordering: Kendall's Tau

Mirella Lapata*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

This article considers the automatic evaluation of information ordering, a task underlying many text-based applications such as concept-to-text generation and multidocument summarization. We propose an evaluation method based on Kendall's r, a metric of rank correlation. The method is inexpensive, robust, and representation independent. We show that Kendall's T correlates reliably with human ratings and reading times.

Original languageEnglish
Pages (from-to)471-484
Number of pages14
JournalComputational Linguistics
Volume32
Issue number4
DOIs
Publication statusPublished - 1 Dec 2006

Fingerprint

Dive into the research topics of 'Automatic evaluation of information ordering: Kendall's Tau'. Together they form a unique fingerprint.

Cite this