<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-2907">
  <Title>Investigating Lexical Substitution Scoring for Subtitle Generation</Title>
  <Section position="8" start_page="50" end_page="51" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> This paper investigated an isolated setting of the lexical substitution task, which has typically been embedded in larger systems and not evaluated directly.</Paragraph>
    <Paragraph position="1"> The setting allowed us to analyze different types of state of the art models and their behavior with respect to characteristic sub-cases of the problem.</Paragraph>
    <Paragraph position="2"> The major conclusion that seems to arise from our experiments is the effectiveness of combining a knowledge based thesaurus such as WordNet with distributional statistical information such as (Lin, 1998), overcoming the known deficiencies of each method alone. Furthermore, modeling the a priori substitution likelihood captures the majority of cases in the evaluated setting, mostly because Word-Net provides a rather noisy set of substitution candidates. On the other hand, successfully incorporating local and global contextual information, as similar to WSD methods, remains a challenging task for future research. Overall, scoring lexical substitutions  is an important component in many applications and we expect that our findings are likely to be broadly applicable.</Paragraph>
  </Section>
class="xml-element"></Paper>