<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1124">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics A Hierarchical Bayesian Language Model based on Pitman-Yor Processes</Title>
  <Section position="10" start_page="990" end_page="990" type="ackno">
    <SectionTitle>
Acknowledgement
</SectionTitle>
    <Paragraph position="0"> I wish to thank the Lee Kuan Yew Endowment Fund for funding, Joshua Goodman for answering many questions regarding interpolated Kneser-Ney and smoothing techniques, John Blitzer and  step function), and HPYLM (top curve). Right: Break down of cross-entropy on test set as a function of the number of occurrences of test words. Plotted is the sum over test words which occurred c times of cross-entropies of IKN, MKN, HPYLM and HPYCV, where c is as given on the x-axis and MKN is used as a baseline. Lower is better. Both panels are for the full training set and n = 3. helpful comments.</Paragraph>
  </Section>
class="xml-element"></Paper>