<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40"><head><meta http-equiv=Content-Type content="text/html; charset=utf-8"><meta name=Generator content="Microsoft Word 15 (filtered medium)"><style><!--
/* Font Definitions */
@font-face
{font-family:新細明體;
panose-1:2 2 5 0 0 0 0 0 0 0;}
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
{font-family:"\@新細明體";
panose-1:2 1 6 1 0 1 1 1 1 1;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0cm;
margin-bottom:.0001pt;
font-size:12.0pt;
font-family:"新細明體",serif;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:#0563C1;
text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
{mso-style-priority:99;
color:#954F72;
text-decoration:underline;}
p.msonormal0, li.msonormal0, div.msonormal0
{mso-style-name:msonormal;
mso-margin-top-alt:auto;
margin-right:0cm;
mso-margin-bottom-alt:auto;
margin-left:0cm;
font-size:12.0pt;
font-family:"新細明體",serif;}
span.EmailStyle18
{mso-style-type:personal;
font-family:"Calibri",sans-serif;
color:#1F497D;}
span.EmailStyle19
{mso-style-type:personal-reply;
font-family:"Calibri",sans-serif;
color:#1F497D;}
.MsoChpDefault
{mso-style-type:export-only;
font-size:10.0pt;}
@page WordSection1
{size:612.0pt 792.0pt;
margin:72.0pt 90.0pt 72.0pt 90.0pt;}
div.WordSection1
{page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]--></head><body lang=ZH-TW link="#0563C1" vlink="#954F72"><div class=WordSection1><p class=MsoNormal><span lang=EN-US style='font-family:"Calibri",sans-serif;color:#1F497D'>Sorry. I have already found your error cases on the</span><span lang=EN-US style='font-family:"Calibri",sans-serif;color:#1F497D'> training-set. Just training-set performance is enough. Thanks.<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-family:"Calibri",sans-serif;color:#1F497D'><o:p> </o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-family:"Calibri",sans-serif;color:#1F497D'>KY</span><span lang=EN-US style='font-family:"Calibri",sans-serif;color:#1F497D'><o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-family:"Calibri",sans-serif;color:#1F497D'><o:p> </o:p></span></p><div><div style='border:none;border-top:solid #E1E1E1 1.0pt;padding:3.0pt 0cm 0cm 0cm'><p class=MsoNormal><b><span lang=EN-US style='font-size:11.0pt;font-family:"Calibri",sans-serif'>From:</span></b><span lang=EN-US style='font-size:11.0pt;font-family:"Calibri",sans-serif'> most-ai-contest-bounces@iis.sinica.edu.tw [mailto:most-ai-contest-bounces@iis.sinica.edu.tw] <b>On Behalf Of </b>kysu<br><b>Sent:</b> Wednesday, April 1, 2020 10:08 PM<br><b>To:</b> '</span><span style='font-size:11.0pt'>闍怵羅</span><span lang=EN-US style='font-size:11.0pt;font-family:"Calibri",sans-serif'>' <s2w81234@gmail.com>; 'Most-ai Contest' <Most-ai-contest@iis.sinica.edu.tw><br><b>Subject:</b> Re: [Most-ai-contest] Multi-spans extraction v18_b20<o:p></o:p></span></p></div></div><p class=MsoNormal><span lang=EN-US><o:p> </o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-family:"Calibri",sans-serif;color:#1F497D'>Thanks! Could you please also show us the performance (also the error cases) on the training-set?<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-family:"Calibri",sans-serif;color:#1F497D'><o:p> </o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-family:"Calibri",sans-serif;color:#1F497D'>KY<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-family:"Calibri",sans-serif;color:#1F497D'><o:p> </o:p></span></p><p class=MsoNormal><b><span lang=EN-US style='font-size:11.0pt;font-family:"Calibri",sans-serif'>From:</span></b><span lang=EN-US style='font-size:11.0pt;font-family:"Calibri",sans-serif'> <a href="mailto:most-ai-contest-bounces@iis.sinica.edu.tw">most-ai-contest-bounces@iis.sinica.edu.tw</a> [<a href="mailto:most-ai-contest-bounces@iis.sinica.edu.tw">mailto:most-ai-contest-bounces@iis.sinica.edu.tw</a>] <b>On Behalf Of </b></span><span style='font-size:11.0pt'>闍怵羅</span><span lang=EN-US style='font-size:11.0pt;font-family:"Calibri",sans-serif'><br><b>Sent:</b> Wednesday, April 1, 2020 6:31 PM<br><b>To:</b> Most-ai Contest <<a href="mailto:Most-ai-contest@iis.sinica.edu.tw">Most-ai-contest@iis.sinica.edu.tw</a>><br><b>Subject:</b> [Most-ai-contest] Multi-spans extraction v18_b20<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US><o:p> </o:p></span></p><div><p class=MsoNormal>各位好，<span lang=EN-US><o:p></o:p></span></p><div><p class=MsoNormal>抱歉拖了這麼久才更新。<span lang=EN-US><o:p></o:p></span></p></div><div><p class=MsoNormal>附件包含兩個檔案：<span lang=EN-US><o:p></o:p></span></p></div><div><p class=MsoNormal><span lang=EN-US>MSPE_v18_branchy20.py <</span>整合的時候，只要把之前的檔案覆蓋即可<span lang=EN-US>><o:p></o:p></span></p></div><div><p class=MsoNormal><span lang=EN-US>MSPE_error.pdf <</span>包含目前的整體情況，以及錯誤的每一題的文章、題目、預測、答案。<span lang=EN-US>><o:p></o:p></span></p></div><div><p class=MsoNormal><span lang=EN-US><</span>由於包含文章，所以頁數非常多，已經有做整理。<span lang=EN-US>><o:p></o:p></span></p></div><div><p class=MsoNormal><span lang=EN-US><o:p> </o:p></span></p></div><div><p class=MsoNormal><span lang=EN-US>=================<o:p></o:p></span></p></div><div><p class=MsoNormal>目前<span lang=EN-US>MSPE</span>的情況如下：<span lang=EN-US><o:p></o:p></span></p></div><div><p class=MsoNormal>一：已有採用<span lang=EN-US>gold support evidence </span>去取答案的版本，但是效果是幾乎沒有差別的。<span lang=EN-US><o:p></o:p></span></p></div><div><p class=MsoNormal>原因是：在原本的<span lang=EN-US>5</span>種模型去<span lang=EN-US>ensemble</span>的情況，就幾乎都包含原本的<span lang=EN-US> gold support evidence</span>的句子。<span lang=EN-US><br></span>也就是說，當我從每個<span lang=EN-US> gold support evidence </span>去取<span lang=EN-US>answer</span>的時候，對於原本的模型來說，是幾乎取出差不多的答案的。<span lang=EN-US><br></span>二：從問題直接提取相關的答案，還在撰寫，但是目前能救的題目，也幾乎被新版的<span lang=EN-US>MSPE</span>解決了，所以可能不會有更好的效果。<span lang=EN-US><br></span>三：目前剩下錯誤的題目，幾乎都是沒有夠多的答案。<span lang=EN-US><o:p></o:p></span></p></div><div><p class=MsoNormal><span lang=EN-US><o:p> </o:p></span></p></div></div></div></body></html>