Evaluating Centering-Based Metrics of Coherence

Nikiforos Karamanis, Massimo Poesio, Chris Mellish, Jon Oberlander

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We use a reliably annotated corpus to compare metrics of coherence based on Centering Theory with respect to their potential usefulness for text structuring in natural language generation. Previous corpus-based evaluations of the coherence of text according to Centering did not compare the coherence of the chosen text structure with that of the possible alternatives. A corpus-based methodology is presented which distinguishes between Centering-based metrics taking these alternatives into account, and represents therefore a more appropriate way to evaluate Centering from a text structuring perspective
Original languageEnglish
Title of host publicationProceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-04)
PublisherACL Anthology
Publication statusPublished - 2004

Cite this