Dave Howcroft<p>In my own work, I'm working to adapt simpler models which are not as data-hungry to perform data-to-text <a href="https://mastodon.social/tags/NLG" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NLG</span></a> in <a href="https://mastodon.social/tags/LowResource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LowResource</span></a> settings. Part of this effort will involve exploring <a href="https://mastodon.social/tags/MultitaskLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MultitaskLearning</span></a> and <a href="https://mastodon.social/tags/Pipeline" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Pipeline</span></a> approaches to neural <a href="https://mastodon.social/tags/NaturalLanguageGeneration" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NaturalLanguageGeneration</span></a>. </p><p>Follow me if you want more content related to these topics, though be advised that this is a whole-person account and I will talk about things other than work as well.</p>