<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Archiving and Interchange DTD v1.0 20120330//EN" "JATS-archivearticle1.dtd">
<article xmlns:xlink="http://www.w3.org/1999/xlink">
  <front>
    <journal-meta />
    <article-meta>
      <title-group>
        <article-title>Creative Support Companions: Some Ideas</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <string-name>Professor of Education at</string-name>
          <xref ref-type="aff" rid="aff0">0</xref>
        </contrib>
        <aff id="aff0">
          <label>0</label>
          <institution>Northwestern University</institution>
        </aff>
      </contrib-group>
      <pub-date>
        <year>2017</year>
      </pub-date>
      <abstract>
        <p />
      </abstract>
    </article-meta>
  </front>
  <body>
    <sec id="sec-1">
      <title>-</title>
      <p>An exciting opportunity for AI is the development of intelligent
assistants that, working with people, enable them to do far more than they
can alone. What would that mean for creative activities? This talk
explores some ideas for using the Companion cognitive architecture to
create software collaborators that support creative work. Companions
include human-like analogical processing, facilities for natural language
and sketch understanding, and rich relational representations that
capture aspects of human visual, spatial, and conceptual knowledge. For
supporting creative activities, this should enable them to (1) help
suggest and explore cross-domain analogies, (2) interact via natural
modalities, providing higher communication bandwidth and reducing friction
compared to software tools, and (3) adapt to their human partners over
time, building up a portfolio of joint work that can be drawn upon in
future e orts.</p>
    </sec>
  </body>
  <back>
    <ref-list />
  </back>
</article>