<?xml version="1.0" standalone="yes"?>
<Paper uid="J96-4003">
  <Title>Learning Bias and Phonological-Rule Induction</Title>
  <Section position="9" start_page="526" end_page="527" type="concl">
    <SectionTitle>
9. Conclusion
</SectionTitle>
    <Paragraph position="0"> Our goal in this paper has been to explore the role of prior knowledge in phonological learning. We showed that a domain-independent, empiricist induction algorithm, OSTIA, failed to induce minimal transducers even for very simple rules like flapping.</Paragraph>
    <Paragraph position="1"> But adding three domain-specific learning biases to OSTIA allowed it to successfully learn transducers implementing simple phonological rules of English and German: faithfulness (underlying segments tend to be realized similarly on the surface), community (similar segments behave similarly), and context (phonological rules need access to variables in their context). These biases are so fundamental to generative phonology that, although they are present in some respect in every phonological theory, they are left implicit in most. Furthermore, we have shown that some of the remaining errors in our augmented model are due to implicit biases in the traditional SPE-style rewrite system that are not similarly represented in the transducer formalism, suggesting that while transducers may be formally equivalent to rewrite rules, they may not have identical evaluation procedures.</Paragraph>
    <Paragraph position="2"> Because our biases were applied to the learning of very simple SPE-style rules, and to a nonprobabilistic theory of purely deterministic transducers, we do not expect that our model as implemented has any practical use as a phonological learning device.</Paragraph>
    <Paragraph position="3"> Indeed, because of the noise and nondeterminism inherent to linguistic data, we feel strongly that stochastic algorithms for language induction are much more likely to be a fruitful research direction (e.g., Kupiec 1992; Lucke 1993; Stolcke and Omohundro 1993, 1994; Ron, Singer, and Tishby 1994). But we believe that the biases we have relied on to improve the OSTIA algorithm may also prove useful when applied to such stochastic linguistic-rule induction algorithms. For example Wooters and Stolcke  Computational Linguistics Volume 22, Number 4 (1994) used the Stolcke and Omohundro model-merging algorithm to induce word-pronunciation HMMs for a speech recognition system. This algorithm has no domain knowledge about phonology, and so is unable to classify together similar phones, or generalize across phones that were missing in the input data. Adding phonological feature biases to such a model could improve its generalization performance just as it improved OSTIA.</Paragraph>
    <Paragraph position="4"> In summary, we believe that augmenting an empirical learning element with relatively abstract learning biases is a very fruitful ground for research between the often restated strict nativist and strict empiricist language learning paradigms.</Paragraph>
  </Section>
class="xml-element"></Paper>