<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-1006">
  <Title>From Elementary Discourse Units to Complex Ones</Title>
  <Section position="8" start_page="53" end_page="54" type="concl">
    <SectionTitle>
7 Conclusion
</SectionTitle>
    <Paragraph position="0"> Starting from the question what are the elementary units to consider for a text's discourse structure, I presented an account for prepositional phrases with adjunct-status as discourse units. Prepositions can be seen as a kind of cue-phrase; however, a preposition does not necessarily signal a coherence relation and even if it does is often ambiguous with regard to the coherence relation signaled. Therefore accounting for prepositional phrases as disco~se units requires additional inferences operating on the semantic representation of both PP and its matrix clause.</Paragraph>
    <Paragraph position="1"> The approach neatly carries over to the phenomena of ambiguous cue-phrases. However, this is still not sufficient to account for deriving the discourse structure of texts in general: cue-phrases are by no means always present and even if there is a cue-phrase, detecting the correct attachment point of a new unit is usually not straight-forward.</Paragraph>
    <Paragraph position="2"> As (one step towards) a solution, referential relations between nominal expressions were suggested. The presented algorithm integrates the resolution of anaphora -- which also depends heavily on inferences and domain-knowledge -- with choosing the target unit to which a new unit should connect to: namely, the highest node providing antecedents to all anaphoric expressions in the new unit. In order for this algorithm to operate successful, it is however necessary that this process is started only after all phenomena of intra-sentential coherence relations have been accounted for, which might be done using the combined approach outlined above.</Paragraph>
    <Paragraph position="3"> Returning to the question posed at the beginning of the paper - what is the appropriate size of elementary discourse units - the answer is twofold: first of all, coherence relations can be found to hold between phrases and the clause containing them, so one should indeed start looking for discourse units at the phrase level. However, Syntax requires that the components of sentences group together, and returning to what (Mann and Thompson, 1988) said, sentences have a kind of functional integrity - one that operates on a level that is different from those of phrases. Once this level is reached, larger chunks can be formed, e.g. by referential means.</Paragraph>
    <Paragraph position="4"> The presented approach to cue-phrases as well as the use of referential relations will be implemented in the text understanding system SYNDIKATE (Hahn and Romacker, 1999), in order to account for semantically rich relations between larger text chlmks and the discourse structure of texts in general.</Paragraph>
    <Paragraph position="5"> This, however, will require further understanding of the conditions of the coherence relations involved.</Paragraph>
  </Section>
class="xml-element"></Paper>