<?xml version="1.0" standalone="yes"?>
<Paper uid="P05-1038">
  <Title>Lexicalization in Crosslinguistic Probabilistic Parsing: The Case of French</Title>
  <Section position="11" start_page="311" end_page="311" type="relat">
    <SectionTitle>
8 Related Work
</SectionTitle>
    <Paragraph position="0"> We are not aware of any previous attempts to build a probabilistic, treebank-trained parser for French.</Paragraph>
    <Paragraph position="1"> However, there is work on chunking for French. The group who built the French Treebank (Abeill'e et al., 2000) used a rule-based chunker to automatically annotate the corpus with syntactic structures, which were then manually corrected. They report an unlabeled recall/precision of 94.3/94.2% for opening brackets and 92.2/91.4% for closing brackets, and a label accuracy of 95.6%. This result is not comparable to our results for full parsing.</Paragraph>
    <Paragraph position="2"> Giguet and Vergne (1997) present use a memory-based learner to predict chunks and dependencies between chunks. The system is evaluated on texts from Le Monde (different from the FTB texts). Results are only reported for verb-object dependencies, for which recall/precision is 94.04/96.39%. Again, these results are not comparable to ours, which were obtained using a different corpus, a different dependency scheme, and for a full set of dependencies.</Paragraph>
  </Section>
class="xml-element"></Paper>