<?xml version="1.0" standalone="yes"?>
<Paper uid="N04-2004">
  <Title>A Computational Framework for Non-Lexicalist Semantics</Title>
  <Section position="7" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> A combination of factors in the natural development of computational linguistics as a field has conspired to narrow the diversity of techniques being explored by researchers. While empirical and quantitative research is the mark of a mature field, such an approach is not without its adverse side-effects. Both syntactic and semantic parsing technology faces a classic chicken-and-egg problem. In order for any new framework to become widely adopted, it must prove to be competitive with state-of-the-art systems in terms of performance. However, robust parsing cannot be achieved without either laboriously crafting grammars or a massive dedicated annotation effort (and experience has shown the latter method to be superior). Therein, however, lies the catch: neither effort is likely to be undertaken unless a new framework proves to be quantitatively superior than previously established methodologies. Lacking quantitative measures currently, the merits of my proposed framework can only be gauged on theoretical grounds and its future potential to better capture a variety of linguistic phenomena.</Paragraph>
  </Section>
class="xml-element"></Paper>