<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-2071">
  <Title>Discriminating image senses by clustering with multimodal features</Title>
  <Section position="8" start_page="553" end_page="553" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> It is remarkable how high purity is, considering that we are using relatively simple image and text representation. In most corpora used to date for research on illustrated text, word sense is an entirely secondary phenomenon, whereas our data set was collected as to emphasize possible ambiguities associated with word sense. Our results suggest that a surprisingly degree of the meaning of an illustrated object is exposed on the surface.</Paragraph>
    <Paragraph position="1"> This work is an initial attempt at addressing the ISD problem. Future work will involve learning the algorithm's parameters without supervision, and develop a semantically meaningful image taxonomy. In particular, we intend to explore the notion of iconographic senses; surprisingly good results on image classification by (Chapelle, Haffner, and Vapnik, 1999) using image features suggest that iconography plays an important role in the semantics of images. An important aspect is to enhance our understanding of the interplay between text and image features for this purpose.</Paragraph>
    <Paragraph position="2"> Also, it remains an unsolved problem how to enumerate iconographic senses, and use them in manual annotation and classification. Experimental work with humans performing similar tasks may provide increased insight into this issue, and can also be used to validate clustering performance.</Paragraph>
  </Section>
class="xml-element"></Paper>