<?xml version="1.0" standalone="yes"?>
<Paper uid="H94-1081">
  <Title>Is N-Best Dead?</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1. INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> The N-Best Paradigm \[1\] was introduced originally as a means for integrating the speech recognition and language understanding components of a spoken language system.</Paragraph>
    <Paragraph position="1"> Since then, we have generalized its use for integrating into the recognition search other expensive knowledge sources (such as higher-order n-gram language models, between-word co-articulation models, and segmental models) without increasing the search space \[2\]. The basic idea is that we use inexpensive knowledge sources to find N alternative sentence hypotheses. Then we rescore each of these hypotheses with the more expensive and more accurate knowledge sources in order to determine the most likely utterance. The N-Best Paradigm specifically, and multi-pass search algofithms in general, are now used widely by the speech recognition research community.</Paragraph>
    <Paragraph position="2"> Besides its use as an efficient search strategy, the N-Best Paradigm has been used extensively in several other ways \[2\]. Its simplicity has made it ideal as a means for cooperation between research sites. For example, we regularly send the N-Best lists of alternatives to research sites that do not have an advanced speech recognition capability (e.g., Paramax and NYU) in order that they can apply their own linguistic components for understanding or for research into alternative language modeling techniques.</Paragraph>
    <Paragraph position="3"> Another related use of the N-Best lists is for evaluation of alternative knowledge sources. New knowledge sources can be evaluated without having to integrate them into the search strategy. For example, we can determine whether a new prosodic module or linguistic knowledge source reduces the error rate when used to reorder the N-Best list. This is particularly important for knowledge sources that are not easily formulated in a left-to-ddght incremental manner.</Paragraph>
    <Paragraph position="4"> Finally, we have presented techniques for optimizing the weights for different knowledge sources, and for discriminative training \[2\].</Paragraph>
    <Paragraph position="5"> In this paper we attempt to determine whether the N-Best Paradigm results in substantial search errors. If it does, then its use for the other purposes mentioned above would also be questionable. First we describe briefly how we used the N-Best paradigm in previous versions of BYBLOS. Then, we descfibe our attempts to avoid the errors that might be a result of using the N-Best paradigm. Finally, we argue that there will always be cases where the N-Best paradigm will make it possible to use some knowledge sources that would likely never be used otherwise.</Paragraph>
  </Section>
class="xml-element"></Paper>