<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-1015">
  <Title>You'll Take the High Road and I'll Take the Low Road: Using a Third Language to hnprove Bilingual Word Alignment</Title>
  <Section position="6" start_page="112" end_page="112" type="evalu">
    <SectionTitle>
7 Discussion and conclusions
</SectionTitle>
    <Paragraph position="0"> With the new experimental setup, we conlirmed the results fiom the earlier experiment, i.e., recall increases, but precision does not suffer.</Paragraph>
    <Paragraph position="1"> This tendency is even more marked in the new series of experiments, in addition, there seems to be a clear division along genetic lines; Polish is the best pivot language for Swedish-Serbian-Bosnian-Croatian alignment, and vice versa, while Spanish works better together with English. Another subcorpus in the ETAP project contains a Finnish part, and we aim at investigating the effects of using this non-Indo-European language (all the languages are Indo-European in the two experiments described here) as one of the languages in a similar experiment It seemed that the choice of content words (or rather: lower-frequency words) over function words did lead to a better result, but this should be t'urther investigated.</Paragraph>
    <Paragraph position="2"> We also see that the more languages we add, the better the results become, i.e., different additional languages complement each other.</Paragraph>
    <Paragraph position="3"> In general, there was little overlap in the contributions that each language added to the final result.</Paragraph>
    <Paragraph position="4"> It should be mentioned at this point, that the sampling and annotation procedure used did not allow us to check up on incorrect alignments which may have propagated through the pivot language. The sampling procedure would have to be redesigned for this to be possible, 7 which we plan to do in the future.</Paragraph>
    <Paragraph position="5"> For the same reason, we do not have all the data needed to calculate the significance of the results. Thus, the results will have to remain suggestive for the time being, although the suggestion is strong that pivot alignment works the way it was hypothesized to work.</Paragraph>
    <Paragraph position="6"> In sc.:nmary, the results are encouraging, in that the links added through pivot alignment were largely correct links, i.e. pivot alignment could be expected to make a positive and safe contribution--i.e, increasing recall without lowering precision--in a word alignment system as one of many independent knowledge sources.</Paragraph>
  </Section>
class="xml-element"></Paper>