<node id="375141">
  <nid>375141</nid>
  <type>external_news</type>
  <uid>
    <user id="28008"><![CDATA[28008]]></user>
  </uid>
  <created>1423501723</created>
  <changed>1475893432</changed>
  <title><![CDATA[Once upon a bot: can we teach computers to write fiction?]]></title>
  <body><![CDATA[<p>This month, several thousand aspiring authors are attempting to write a novel in 30 days. They are taking part in an annual event known as<a class=" u-underline" href="http://nanowrimo.org/" data-link-name="in body link" data-component="in-body-link">NaNoWriMo</a>, National Novel Writing Month, in the hope that the time pressure will spur them on. For a small community of computer programmers, though, NaNoWriMo has a lighthearted sister competition:&nbsp;<a class=" u-underline" href="https://github.com/dariusk/NaNoGenMo-2014/issues" data-link-name="in body link" data-component="in-body-link">National Novel Generating Month</a>, the goal of which is to teach a computer to write a novel for you.</p><p>However, finished NaNoGenMo projects are unlikely to trouble Booker judges. They include a version of Moby-Dick in which the words have been&nbsp;<a class=" u-underline" href="https://raw.githubusercontent.com/hugovk/meow.py/master/meow-x2-pg2701.txt" data-link-name="in body link" data-component="in-body-link">swapped for meows</a>&nbsp;of the same length (immortal opening line: Meow me Meeeeow); another version in which a few key words have been swapped out for emoji; and a novel made up of unconnected excerpts from an online database of&nbsp;<a class=" u-underline" href="https://github.com/dariusk/NaNoGenMo/issues/2" data-link-name="in body link" data-component="in-body-link">teenage girls’ accounts of their dreams</a>.</p><p><a class=" u-underline" href="https://research.cc.gatech.edu/eilab/mark-riedl" data-link-name="in body link" data-component="in-body-link">Mark Riedl</a>, an associate professor at the Georgia Institute of Technology, is not taking part in NaNoGenMo. But he and his colleagues are among the many computer scientists working on far more sophisticated digital storytellers. For the past two years, they have been tinkering with a program called&nbsp;<a class=" u-underline" href="https://research.cc.gatech.edu/eilab/open-story-generation" data-link-name="in body link" data-component="in-body-link">Scheherazade</a>, which learns how to describe tasks by analysing crowd-sourced human accounts, and then attempts to produce plausible short stories about, say, going to the movies or a restaurant.</p>]]></body>
  <field_article_url>
    <item>
      <url><![CDATA[http://www.theguardian.com/books/2014/nov/11/can-computers-write-fiction-artificial-intelligence]]></url>
      <title><![CDATA[]]></title>
    </item>
  </field_article_url>
  <field_publication>
    <item>
      <value><![CDATA[ Christine Angelini ]]></value>
    </item>
  </field_publication>
  <field_dateline>
    <item>
      <value>2014-11-11</value>
      <timezone></timezone>
    </item>
  </field_dateline>
  <field_media>
        </field_media>
  <og_groups>
          <item>69599</item>
      </og_groups>
  <og_groups_both>
          <item><![CDATA[IPaT]]></item>
      </og_groups_both>
    <field_userdata><![CDATA[]]></field_userdata>
</node>
