<?xml version="1.0" standalone="yes"?>
<Paper uid="I05-2025">
  <Title>Investigating the features that affect cue usage of non-native speakers of English</Title>
  <Section position="8" start_page="148" end_page="148" type="concl">
    <SectionTitle>
8 Conclusion
</SectionTitle>
    <Paragraph position="0"> This study proves that the placement of because is connected with reading ease. We used a machine learning program to induce the best classification model of placement of because for non-native speakers. The experiment results show that discourse relation of embedding structure is the most powerful feature to predict the placement of because. E.g., when relation is &amp;quot;cause&amp;quot;, &amp;quot;contrast&amp;quot;, &amp;quot;example&amp;quot; or &amp;quot;explanation&amp;quot;, because occurs in the first span. The heuristics obtained from machine learning experiments can be applied to NLG systems.</Paragraph>
  </Section>
class="xml-element"></Paper>