Paper: Paragraph- Word- And Coherence-Based Approaches To Sentence Ranking: A Comparison Of Algorithm And Human Performance

ACL ID P04-1049
Title Paragraph- Word- And Coherence-Based Approaches To Sentence Ranking: A Comparison Of Algorithm And Human Performance
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2004
Authors

Sentence ranking is a crucial part of generating text summaries. We compared human sentence rankings obtained in a psycholinguistic experiment to three different approaches to sentence ranking: A simple paragraph-based approach intended as a baseline, two word-based approaches, and two coherence-based approaches. In the paragraph-based approach, sentences in the beginning of paragraphs received higher importance ratings than other sentences. The word-based approaches determined sentence rankings based on relative word frequencies (Luhn (1958); Salton & Buckley (1988)). Coherence-based approaches determined sentence rankings based on some property of the coherence structure of a text (Marcu (2000); Page et al. (1998)). Our results suggest poor performance for the simple paragraph-based appr...