<meta http-equiv="Content-Type" content="text/html; charset=GB18030"><div><p class="MsoNormal"><span lang="EN-US" style="mso-ansi-language:EN-US">Hi
Adapters,<o:p></o:p></span></p>
<p class="MsoNormal"><font __editorwarp__="1" style="display: inline; font-size: 14px; font-family: Verdana; color: rgb(0, 0, 0); background-color: rgba(0, 0, 0, 0); font-weight: 400; font-style: normal;">Today IĄŻll continue to talk
about evaluation method of summarization with a paper from ACL 2020 : Fact-based
Content Weighting for Evaluating Abstractive Summarisation. This evaluation method is neither a classic reference-based evaluation nor a reference-less approach, but a combination of these two. T</font><span lang="EN-US" style="text-indent: -18pt;">here are two key ideas of this paper: one is the idea of
using both source text and reference summary for evaluation, another is to take
the semantic structure of source text into consideration. Hope you enjoy it.</span></p><p class="MsoListParagraph" style="text-indent:-18.0pt;mso-list:l0 level1 lfo1"><span lang="EN-US"><o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="mso-ansi-language:EN-US">Best Wishes,<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="mso-ansi-language:EN-US">Yvonne
Huang<o:p></o:p></span></p><br></div>