<?xml version="1.0" standalone="yes"?>
<Paper uid="I05-2029">
  <Title>Multi-Modal Question-Answering: Questions without Keyboards</Title>
  <Section position="9" start_page="171" end_page="171" type="concl">
    <SectionTitle>
8 Conclusions
</SectionTitle>
    <Paragraph position="0"> In this paper we have described our approach to allowing users to specify queries by interacting with virtual photographs that have been annotated with semantic information. While this approach is clearly more limited than allowing full text input, it is useful for applications like games that do not always have a keyboard available.</Paragraph>
  </Section>
class="xml-element"></Paper>