<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-2007">
  <Title>Using an incremental robust parser to automatically generate semantic UNL graphs</Title>
  <Section position="8" start_page="10" end_page="11" type="concl">
    <SectionTitle>
6 Discussion
</SectionTitle>
    <Paragraph position="0"> At this stage of the project, there are a number of conclusions we can draw from the preceding evaluation.</Paragraph>
    <Paragraph position="1"> The first one is that the results are rather encouraging in terms of a first rough enconvertion from syntactic XIPF+ information to UNL expressions (agt, obj and mod). However, we are aware that certain cases present considerable difficulties. For example, in addition to the examples presented in the evaluation for verbs of state, subjects with a semantic feature of &amp;quot;patient&amp;quot; are to be enconverted as obj and not as subj (unfortunately the semantic information needed for this transformation is not yet available within the parser). Thus in &amp;quot;La r'eunion continuera jusqu'`acesoir.&amp;quot;  the parser extracts a subj(continuer,r'eunion) that might be enconverted as obj(continue,meeting) in UNL. All these kinds of complex transformations including particular semantic features are at this point an important bottleneck for the enconverter.</Paragraph>
    <Paragraph position="2"> The second conclusion coming from the evaluation (even if not quantitatively analyzed) is that the choice of the UW remains a critical point, as the enconverter has not the possibility of choosing the correct acception giving a configuration. One possibility to consider might be to introduce interactivity with a human to choose the correct UW. The second possibility is related to the improval of the parser: we can consider adding more linguistic information, in the form of semantic classes or semantic features, in order to be able to disambiguate. Having enriched the parser with these semantic features, another possibility to improve the enconverter might be to consider statistical information about collocations.</Paragraph>
    <Paragraph position="3">  Towards accessing cultural diversity.</Paragraph>
    <Paragraph position="4">  The meeting will continue until this evening.</Paragraph>
    <Paragraph position="5"> Finally, we are conscious that there would still remain several aspects which would demand to be improved within the parser itself : prepositionnal attachment disambiguation, scope of coordination, complex coreference, etc. Particular strategies may be adapted to handle such difficulties individually (using statistical information, interactive disambiguation, etc.). 7Conclusion In this paper we have presented a mechanism for automatically producing UNL expressions using the ouput of a robust parser. After describing the UNL formalism and presenting an incremental parser able to accurately process huge amounts of data, we have shown how one can transform the linguistic information provided by the parser into UNL expressions. We have also presented a first evaluation in an attempt to try to assess the performance of the enconverter.</Paragraph>
    <Paragraph position="6"> Our results show that there are still several crucial problems that we need to solve. However, taking into account that this is preliminary work, the results already obtained are encouraging and confirm the possibility of using the reliable linguistic information automatically obtained from an incremental robust parser to create a UNL semantic enconverter for huge amounts of data.</Paragraph>
  </Section>
class="xml-element"></Paper>