<?xml version="1.0" standalone="yes"?>
<Paper uid="P02-1001">
  <Title>Parameter Estimation for Probabilistic Finite-State Transducers</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> Weighted finite-state transducers suffer from the lack of a training algorithm. Training is even harder for transducers that have been assembled via finite-state operations such as composition, minimization, union, concatenation, and closure, as this yields tricky parameter tying. We formulate a &amp;quot;parameterized FST&amp;quot; paradigm and give training algorithms for it, including a general bookkeeping trick (&amp;quot;expectation semirings&amp;quot;) that cleanly and efficiently computes expectations and gradients.</Paragraph>
  </Section>
class="xml-element"></Paper>