<?xml version="1.0" standalone="yes"?>
<Paper uid="P94-1024">
  <Title>Not Sink Sink</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> This paper shows how to formally characterize language learning in a finite parameter space as a Markov structure, hnportant new language learning results follow directly: explicitly calculated sample complexity learning times under different input distribution assumptions (including CHILDES database language input) and learning regimes. We also briefly describe a new way to formally model (rapid) diachronic syntax change.</Paragraph>
  </Section>
class="xml-element"></Paper>