<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-3203">
  <Title>Learning Quantity Insensitive Stress Systems via Local Inference</Title>
  <Section position="6" start_page="27" end_page="27" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> This paper presented a batch learner which correctly infers the attested QI stress patterns from surface forms. The key to the success of this learner is that it takes advantage of a universal property of QI stress systems, neighborhood-distinctness. This property provides a natural explanation for why stress falls within a particular window of the word edge and why rhythms are binary and ternary. It is striking that all of the attested patterns are learned by this simple approach, suggesting that it will be fruitful and revealing when applied to other phonotactic learning problems.</Paragraph>
  </Section>
class="xml-element"></Paper>