<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-1004">
  <Title>Paragraph-, word-, and coherence-based approaches to sentence ranking: A comparison of algorithm and human performance</Title>
  <Section position="2" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> 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 &amp; Buckley (1988)).</Paragraph>
    <Paragraph position="1"> 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 approach, whereas word-based approaches perform remarkably well. The best performance was achieved by a coherence-based approach where coherence structures are represented in a non-tree structure.</Paragraph>
    <Paragraph position="2"> Most approaches also outperformed the commercially available MSWord summarizer.</Paragraph>
  </Section>
class="xml-element"></Paper>