<html><body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><br class=""><br class=""><blockquote type="cite" class="">On 21 Aug 2020, at 12:35, Stephan Oepen <<a href="mailto:oe@ifi.uio.no" class="">oe@ifi.uio.no</a>> wrote:<br class=""><br class="">one used to do this kind of evaluation in [incr tsdb()], initiated<br class="">through the 'Trees | Score' command.  i am not sure this will work out<br class="">of the box for comparing an FFTB-based treebank to an ACE-generated<br class="">parsing profile ... although it should, in principle!  i expect you<br class="">would want to select 'Result Equivalence' and 'Score All Items' in<br class="">'Trees | Switches', and just give it a shot :-).<br class=""><br class="">if you get the above to work (which should give exact match<br class="">accuracies), the [incr tsdb()] scorer can also compute a range of<br class="">additional metrics, including EDM and ParsEval, but these would have<br class="">to be activated programmatically:<br class=""><br class="">(setf *redwoods-score-counts* '(:ta :parseval :edma :edmp))<br class=""><br class=""></blockquote><div class=""><br class=""></div>Hi Stephan,<div class=""><br class=""></div><div class="">Thank you for the directions. Trying that first approach, it gave me 100% accuracy?? But the window with the results opened instantaneously, I don’t believe it really did the analysis. How to make sure the tool is doing what we excepted it to do? How can I know if the two profiles are proper selected?<br class=""><br class=""><div class=""><br class=""></div><div class=""><img apple-inline="no" id="981408E7-D096-433F-AEA4-46F3F1B05F9A" src="cid:A02796A7-6E7A-4624-AEF1-F6D649DAFDCD@br" class=""></div><div class=""><br class=""></div><div class="">Best,</div><div class="">Alexandre</div><div class=""><br class=""></div><div class=""><br class=""></div><div class=""><br class=""><br class=""></div></div></body></html>