<?xml version="1.0" standalone="yes"?>
<Paper uid="H05-1065">
  <Title>Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP), pages 515-522, Vancouver, October 2005. c(c)2005 Association for Computational Linguistics Disambiguation of Morphological Structure using a PCFG</Title>
  <Section position="11" start_page="521" end_page="521" type="ackno">
    <SectionTitle>
10 Future Work
</SectionTitle>
    <Paragraph position="0"> There are several starting points for improvement.</Paragraph>
    <Paragraph position="1"> Guidelines should be developed for the manual annotationofdatainordertomakeitlessdependenton null the annotator's intuitions. More data should be annotated to create a treebank of morphological analyses. Given such a treebank, the parser could be trained on labeled data or on a combination of labeled and unlabeled data, which presumably would further increase the parsing accuracy.</Paragraph>
  </Section>
class="xml-element"></Paper>