<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-1078">
  <Title>Chart-Based Transfer Rule Application in Machine Translation</Title>
  <Section position="9" start_page="541" end_page="542" type="concl">
    <SectionTitle>
8 Future Work
</SectionTitle>
    <Paragraph position="0"> Fnture work should address two limitations of our current system: (1) Bad parses yield bad transihr rules; and (2) sparse data limits the size of our transfer rule database and our options for  applying transfer rules selectively. To nttack the &amp;quot;bad parse&amp;quot; problem, we are eonsideriug using our MT system with less-detailed parsers, since these parsers typically produce less error-prone output. We will have to conduct exl)erimcnts to determine the minimum level of detM1 that is needed, a Previous to the work reported in this paper, we ran our MT system on bilinguM corpora in which the sentences were Migned manuMly. The cost of manuM aligmnent limited the size of the corpora we could use. A lot of our recent MT research has bo.en tbcused on solving this sparse data prol)lem through our develoi)ment of a sentence alignment progrmn (Meyers et al., 1998a). We now have 300,000 automaticMly aligned sentences in the Microsoft help text domain tbr future experiineni;s. In addition to provi(ting us with many more transfer rules, this shouhl Mlow us to colh'.ct transfer rule co-occurrence information which we c~m then use to apply tr;mstbr rules more effectively, perhaps improving transb~tion quality. In a preliminary experime, nt ahmg these lines using the Experiment 1. tort)us, co-occurrence information had no noticeable ef feet. However, we are hot)eflfl that flltm'e ext)eriments with 300,000 Migned sentences (300 tinies as nnlch data) will 1)e more successful.</Paragraph>
    <Paragraph position="1"> SOne could set u 1) a contimmm from detailed parsers like Proteus down to shallow verb-group/noun-grouI) recognizers, with the Penn treetmnk based parsers lying somewhere in the middle. As one travels down t, he eonLinlmIn t;o t;he lower detail parsers, tim error rate naturally decreases.</Paragraph>
  </Section>
class="xml-element"></Paper>