<?xml version="1.0" standalone="yes"?>
<Paper uid="E95-1033">
  <Title>ParseTalk about Sentenceand Text-Level Anaphora</Title>
  <Section position="7" start_page="243" end_page="243" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> We have outlined a model of anaphora resolution which is founded on a dependency-based grammar model. This model accounts for sentence-level anaphora, with constraints adapted from GB, as well as text-level anaphora, with concepts close to Grosz-Sidner-style focus models. The associated text parser is based on the actor computation model. Its message passing mechanisms constitute the foundation for expressing specific linguistic protocols, e.g., that for anaphora resolution. The main advantage of our approach lies in the unified framework for sentence- and text-level anaphora, using a coherent grammar format, and the provision for access to grammatical and conceptual knowledge without prioritizing either one of them.</Paragraph>
    <Paragraph position="1"> It is also a striking fact that, given the same linguistic phenomena, structural dependency configurations are considerably simpler than their GB counterparts, though suitably expressive.</Paragraph>
    <Paragraph position="2"> The anaphora resolution module (for reflexives, intra- and inter-sentential anaphora) has been realized as part of ParseTalk, a dependency parser which forms part of a larger text understanding system for the German language, currently under development at our laboratory. The parser has been implemented in Smalltalk; the Smalltalk system itself, which runs on a SUN SparcStation network, has been extended by asynchronous message passing facilities and physical distribution mechanisms (Xu, 1993). The current lexicon contains a hierarchy of approximately 100 word class specifications with nearly 3.000 lexical entries and corresponding concept descriptions from two domains (information technology and medicine) available from the LOOM knowledge representation system (MacGregor and Bates, 1987).</Paragraph>
    <Paragraph position="3"> Acknowledgments. We would like to thank our col- leagues in the CZ~Z) r group who read earlier versions of this paper. In particular, improvements are due to discussions we had with S. Schacht, N. Br6ker, P. Neuhaus, and M. Klenner. We also like to thank J. Alcantara (CorneU U) who kindly took the role of the native speaker via Internet. This work has been funded by LGFG Baden- Wiirttemberg (1.1.4-7631.0; M. Strube) and a grant from DFG (Ha 2907/1-3; U. Hahn).</Paragraph>
  </Section>
class="xml-element"></Paper>