<?xml version="1.0" standalone="yes"?>
<Paper uid="P92-1017">
  <Title>eling for speech recognition. In Sadaoki Furui and M. Mohan Sondhi, editors, Advances in Speech</Title>
  <Section position="7" start_page="133" end_page="134" type="concl">
    <SectionTitle>
5. CONCLUSIONS AND
FURTHER WORK
</SectionTitle>
    <Paragraph position="0"> We have introduced a modification of the well-known inside-outside algorithm for inferring the parameters of a stochastic context-free grammar that can take advantage of constituent information (constituent bracketing) in a partially bracketed corpus.</Paragraph>
    <Paragraph position="1"> The method has been successfully applied to SCFG inference for formal languages and for part-of-speech sequences derived from the ATIS  spoken-language corpus.</Paragraph>
    <Paragraph position="2"> The use of partially bracketed corpus can reduce the number of iterations required for convergence of parameter reestimation. In some cases, a good solution is found from a bracketed corpus but not from raw text. Most importantly, the use of partially bracketed natural corpus enables the algorithm to infer grammars specifying linguistically reasonable constituent boundaries that cannot be inferred by the inside-outside algorithm on raw text. While none of this is very surprising, it supplies some support for the view that purely unsupervised, self-organizing grammar inference methods may have difficulty in distinguishing between underlying grammatical structure and contingent distributional regularities, or, to put it in another way, it gives some evidence for the importance of nondistributional regularities in language, which in the case of bracketed training have been supplied indirectly by the linguists carrying out the bracketing.</Paragraph>
    <Paragraph position="3"> Also of practical importance, the new algorithm can have better time complexity for bracketed text. In the best situation, that of a training set with full binary-branching bracketing, the time for each iteration is in fact linear on the total length of the set.</Paragraph>
    <Paragraph position="4"> These preliminary investigations could be extended in several ways. First, it is important to determine the sensitivity of the training algorithm to the initial probability assignments and training corpus, as well as to lack or misplacement of brackets. We have started experiments in this direction, but reasonable statistical models of bracket elision and misplacement are lacking.</Paragraph>
    <Paragraph position="5"> Second, we would like to extend our experiments to larger terminal vocabularies. As is well known, this raises both computational and data sparseness problems, so clustering of terminal symbols will be essential.</Paragraph>
    <Paragraph position="6"> Finally, this work does not address a central weakness of SCFGs, their inability to represent lexical influences on distribution except by a statistically and computationally impractical proliferation of nonterminal symbols. One might instead look into versions of the current algorithm for more lexically-oriented formalisms such as stochastic lexicalized tree-adjoining grammars (Schabes, 1992).</Paragraph>
  </Section>
class="xml-element"></Paper>