<?xml version="1.0" standalone="yes"?>
<Paper uid="P91-1017">
  <Title>Two Languages Are More Informative Than One *</Title>
  <Section position="8" start_page="135" end_page="136" type="concl">
    <SectionTitle>
7 Conclusions
</SectionTitle>
    <Paragraph position="0"> The method presented takes advantage of two linguistic phenomena: the different usage of words and word senses among different languages and the importance of lexical cooccurrences within syntactic relations. The experiment shows that these phenomena are indeed useful for practical disambiguation.</Paragraph>
    <Paragraph position="1"> We suggest that the high precision received in the experiment relies on two characteristics of the am- null biguity phenomena, namely the sparseness and redundancy of the disambiguating data. By sparseness we mean that within the large space of alternative interpretations produced by ambiguous utterances, only a small portion is commonly used. Therefore the chance of an inappropriate interpretation to be observed in the corpus (in other contexts) is low.</Paragraph>
    <Paragraph position="2"> Redundancy relates to the fact that different informants (such as different lexical relations or deep understanding) tend to support rather than contradict one another, and therefore the chance of picking a &amp;quot;wrong&amp;quot; informant is low.</Paragraph>
    <Paragraph position="3"> The examination of the failures suggests that future research may improve both the applicability and precision of the model. Our next goal is to handle inapplicable cases by using cooccurrence data regardless of syntactic relations and similarities between words. We expect that increasing the applicability will lead to some decrease in precision, similar to the tradeoff between recall and precision in information retrieval. Pursuing this tradeoff will improve the performance of the method and reveal its limitations.</Paragraph>
  </Section>
class="xml-element"></Paper>