<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-3813">
  <Title>Matching Syntactic-Semantic Graphs for Semantic Relation Assignment</Title>
  <Section position="8" start_page="86" end_page="87" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> We have shown through the results gathered from an interactive and incremental text processing system that syntactic-semantic graph-matching can be used with good results for semantic analysis of texts. The graph-matching heuristic clearly dominates other heuristics used, and it learns to make better predictions as more examples accumulate.</Paragraph>
    <Paragraph position="1"> Graph-matching is most useful for assigning semantic relations between verbs and their arguments, but it also gives good results for inter-clause relations. At the noun-phrase level, we could only tackle noun-modi er pairs that exhibit a modicum of syntactic structure a connective. For base NPs there is practically nothing that syntactic information can bring to the semantic analysis process.</Paragraph>
    <Paragraph position="2"> The graph-matching process could be improved by bringing into play freely available lexical re- null sources. For now, the actual words in the graph nodes are not used at all. We could use WordNet to compute word similarities, to select closer matching graphs. VerbNet or FrameNet information could help choose graphs centered on verbs with similar syntactic behaviour, as captured by Levin's verb groups (Levin, 1993) which are the basis of VerbNet.</Paragraph>
  </Section>
class="xml-element"></Paper>