<html><body><div style="font-family: arial, helvetica, sans-serif; font-size: 12pt; color: #000000"><div><style></style></div><div></div><div><span style="font-size: 12pt;">Dear all,</span><br></div><div data-marker="__QUOTED_TEXT__"><div style="font-family:'arial' , 'helvetica' , sans-serif;font-size:12pt;color:#000000"><br><div>First we like to congratulate our team pass the first run and our hard work is worthy.</div><br><div>The next run (final run) will be held on 2020/4/8 and we still need your support to go forward the final run.</div><div>The next meeting will be 2020/1/14 12:30 and the agenda is listed as follows for your reference.</div><br><div>1. Discussion of our first run result (including the integration, implementation, and issues for future improvement) by jjfan</div><div>2. Description of your model implementation (including your model/method and which papers referenced in your model if you have)</div><div>3. Prof. Su will give an brief of some important concepts (NN-based, statistics-based, rule-based approaches) for your reference </div><br><div> <p class="MsoListParagraph" style="color:rgb( 0 , 0 , 0 );font-family:'helvetica neue' , 'helvetica' , 'arial' , 'liberation sans' , sans-serif;font-size:14.16px;font-style:normal;font-weight:400;letter-spacing:normal;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;background-color:rgb( 255 , 255 , 255 );margin:0px;padding-left:30px"><span lang="EN-US">1.<span style="font:7pt 'times new roman'"> </span></span><span lang="EN-US">BERT is very inefficient in learning an inference (even it is a simple one)</span></p><p class="MsoListParagraph" style="color:rgb( 0 , 0 , 0 );font-family:'helvetica neue' , 'helvetica' , 'arial' , 'liberation sans' , sans-serif;font-size:14.16px;font-style:normal;font-weight:400;letter-spacing:normal;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;background-color:rgb( 255 , 255 , 255 );margin:0px;padding-left:30px"><span lang="EN-US">2.<span style="font:7pt 'times new roman'"> </span></span><span lang="EN-US">Discrete-Symbol vs. Continuous-Embedding: Discrete-Symbols have no idea about the distance among them (even integers if each integer is regarded as a discrete symbol), and cannot merge their information.</span></p><p class="MsoListParagraph" style="color:rgb( 0 , 0 , 0 );font-family:'helvetica neue' , 'helvetica' , 'arial' , 'liberation sans' , sans-serif;font-size:14.16px;font-style:normal;font-weight:400;letter-spacing:normal;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;background-color:rgb( 255 , 255 , 255 );margin:0px;padding-left:30px"><span lang="EN-US">3.<span style="font:7pt 'times new roman'"> </span></span><span lang="EN-US">Rule/Statistics-based approaches have difficulty to handle synonyms (could be handled by WordNet), similar words, paraphrasing, implication, association.</span></p><p class="MsoListParagraph" style="color:rgb( 0 , 0 , 0 );font-family:'helvetica neue' , 'helvetica' , 'arial' , 'liberation sans' , sans-serif;font-size:14.16px;font-style:normal;font-weight:400;letter-spacing:normal;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;background-color:rgb( 255 , 255 , 255 );margin:0px;padding-left:30px"><span lang="EN-US">4.<span style="font:7pt 'times new roman'"> </span></span><span lang="EN-US">Rule/Statistics-based approaches have difficulty to handle context (they cannot merge them to keep the same dimensionality).</span></p><p class="MsoListParagraph" style="color:rgb( 0 , 0 , 0 );font-family:'helvetica neue' , 'helvetica' , 'arial' , 'liberation sans' , sans-serif;font-size:14.16px;font-style:normal;font-weight:400;letter-spacing:normal;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;background-color:rgb( 255 , 255 , 255 );margin:0px;padding-left:30px"><span lang="EN-US">5.<span style="font:7pt 'times new roman'"> </span></span><span lang="EN-US">NN-based approaches have difficulty to know if two lexicons/NEs are exactly the same</span></p><p class="MsoListParagraph" style="color:rgb( 0 , 0 , 0 );font-family:'helvetica neue' , 'helvetica' , 'arial' , 'liberation sans' , sans-serif;font-size:14.16px;font-style:normal;font-weight:400;letter-spacing:normal;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;background-color:rgb( 255 , 255 , 255 );margin:0px;padding-left:30px"><span lang="EN-US">6.<span style="font:7pt 'times new roman'"> </span></span><span lang="EN-US">NN-based approaches have difficulty to handle long-distance dependency/pattern (e.g., which one should be compared with which one, formatting pattern), aggregative features (e.g., counts, minimum/maximum, intersection, etc.), abstract features (e.g., P and H are the same regardless of their content)</span></p><p class="MsoListParagraph" style="color:rgb( 0 , 0 , 0 );font-family:'helvetica neue' , 'helvetica' , 'arial' , 'liberation sans' , sans-serif;font-size:14.16px;font-style:normal;font-weight:400;letter-spacing:normal;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;background-color:rgb( 255 , 255 , 255 );margin:0px;padding-left:30px"><span lang="EN-US">7.<span style="font:7pt 'times new roman'"> </span></span><span lang="EN-US">We should use NN-based approach to locate the regions, and then use rule-based approach to handle the boundary (which uses formatting regularity).</span></p><p class="MsoListParagraph" style="color:rgb( 0 , 0 , 0 );font-family:'helvetica neue' , 'helvetica' , 'arial' , 'liberation sans' , sans-serif;font-size:14.16px;font-style:normal;font-weight:400;letter-spacing:normal;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;background-color:rgb( 255 , 255 , 255 );margin:0px;padding-left:30px"><span lang="EN-US">8.<span style="font:7pt 'times new roman'"> </span></span><span lang="EN-US">We could use NN-based approach to locate/identify the roles, and then use rule-based approach to handle the inference (e.g., which one is the largest one; how many cities that he visited, etc.).</span></p><p class="MsoListParagraph" style="color:rgb( 0 , 0 , 0 );font-family:'helvetica neue' , 'helvetica' , 'arial' , 'liberation sans' , sans-serif;font-size:14.16px;font-style:normal;font-weight:400;letter-spacing:normal;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;background-color:rgb( 255 , 255 , 255 );margin:0px;padding-left:30px"><span lang="EN-US">9.<span style="font:7pt 'times new roman'"> </span></span><span lang="EN-US">Handle Topic/Focus (Zero anaphora, Omission, implicit implication): (1) Extract explicit topic/focus, (2) Use embedding to approximate topic/focus (e.g., use document-embedding to approximate topic, paragraph/sentence-embedding to approximate focus, RNN to feed in status of previous paragraph/sentence information to approximate zero-anaphora, omission<span style="color:#1f497d">)</span>.</span></p><p class="MsoListParagraph" style="color:rgb( 0 , 0 , 0 );font-family:'helvetica neue' , 'helvetica' , 'arial' , 'liberation sans' , sans-serif;font-size:14.16px;font-style:normal;font-weight:400;letter-spacing:normal;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;background-color:rgb( 255 , 255 , 255 );margin:0px;padding-left:30px"><br></p><p class="MsoListParagraph" style="color:rgb( 0 , 0 , 0 );font-family:'helvetica neue' , 'helvetica' , 'arial' , 'liberation sans' , sans-serif;font-size:14.16px;font-style:normal;font-weight:400;letter-spacing:normal;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;background-color:rgb( 255 , 255 , 255 );margin:0px"><span style="font-size:12pt">4. The plan for the final run</span></p><p class="MsoListParagraph" style="color:rgb( 0 , 0 , 0 );font-family:'helvetica neue' , 'helvetica' , 'arial' , 'liberation sans' , sans-serif;font-size:14.16px;font-style:normal;font-weight:400;letter-spacing:normal;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;background-color:rgb( 255 , 255 , 255 );margin:0px"><span style="font-size:12pt"><br></span></p><p class="MsoListParagraph" style="color:rgb( 0 , 0 , 0 );font-family:'helvetica neue' , 'helvetica' , 'arial' , 'liberation sans' , sans-serif;font-size:14.16px;font-style:normal;font-weight:400;letter-spacing:normal;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;background-color:rgb( 255 , 255 , 255 );margin:0px"><span style="font-size:12pt">Best,</span></p><p class="MsoListParagraph" style="color:rgb( 0 , 0 , 0 );font-family:'helvetica neue' , 'helvetica' , 'arial' , 'liberation sans' , sans-serif;font-size:14.16px;font-style:normal;font-weight:400;letter-spacing:normal;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;background-color:rgb( 255 , 255 , 255 );margin:0px"><span style="font-size:12pt">jjfan</span></p> </div><br><hr id="zwchr"><div><b>From: </b>"kysu" <kysu@iis.sinica.edu.tw><br><b>To: </b>"Most-ai Contest" <Most-ai-contest@iis.sinica.edu.tw><br><b>Cc: </b>"范正忠" <jjfan@iis.sinica.edu.tw>, "kysu" <kysu@iis.sinica.edu.tw><br><b>Sent: </b>Monday, December 30, 2019 8:58:52 AM<br><b>Subject: </b>We have entered the 2020科技大擂台 second/final round!<br></div><br><div><title></title><div><p class="MsoNormal"><span lang="EN-US" style="font-family:'calibri' , sans-serif;color:#1f497d">Dear all,</span><span lang="EN-US" style="font-family:'calibri' , sans-serif"></span></p><p class="MsoNormal"><span lang="EN-US" style="font-family:'calibri' , sans-serif;color:#1f497d"> </span></p><p class="MsoNormal"><span lang="EN-US" style="font-family:'calibri' , sans-serif;color:#1f497d">According to Dr. JJ Fan, we have entered the second/final round (More details will be announced tomorrow, as Dr. JJ Fan will take off today to see a doctor). Thanks a lot for your great effort! We have made it. </span></p><p class="MsoNormal"><span lang="EN-US" style="font-family:'calibri' , sans-serif;color:#1f497d"> </span></p><p class="MsoNormal"><span lang="EN-US" style="font-family:'calibri' , sans-serif;color:#1f497d">KY</span></p><p class="MsoNormal"><span lang="EN-US" style="font-family:'calibri' , sans-serif;color:#1f497d"> </span></p><p class="MsoNormal"><span lang="EN-US" style="font-family:'calibri' , sans-serif;color:#1f497d"> </span></p><div><div style="border:none;border-top:solid #e1e1e1 1pt;padding:3pt 0cm 0cm 0cm"><p class="MsoNormal"><b><span lang="EN-US" style="font-size:11pt;font-family:'calibri' , sans-serif">From:</span></b><span lang="EN-US" style="font-size:11pt;font-family:'calibri' , sans-serif"> </span><span style="font-size:11pt">科技大擂台</span><span lang="EN-US" style="font-size:11pt;font-family:'calibri' , sans-serif"> [<a href="mailto:gitlab@speech.nchc.org.tw" rel="nofollow%20noopener%20noreferrer nofollow noopener noreferrer" target="_blank">mailto:gitlab@speech.nchc.org.tw</a>] <br><b>Sent:</b> Thursday, December 26, 2019 3:29 PM<br><b>To:</b> <a href="mailto:kysu@iis.sinica.edu.tw" rel="nofollow%20noopener%20noreferrer nofollow noopener noreferrer" target="_blank">kysu@iis.sinica.edu.tw</a><br><b>Subject:</b> Re: 2020_fgc_forum | </span><span style="font-size:11pt">【官方公告】【</span><span lang="EN-US" style="font-size:11pt;font-family:'calibri' , sans-serif">2020</span><span style="font-size:11pt">科技大擂台</span><span style="font-size:11pt;font-family:'calibri' , sans-serif"> </span><span style="font-size:11pt">緊急通知】科技大擂台初賽日程調整通知</span><span lang="EN-US" style="font-size:11pt;font-family:'calibri' , sans-serif"> (#40)</span></p></div></div><p class="MsoNormal"><span lang="EN-US"> </span></p><div><p class="details"><i><span lang="EN" style="color:#777777"><a href="https://speech.nchc.org.tw/fgc" rel="nofollow%20noopener%20noreferrer nofollow noopener noreferrer" target="_blank"><span lang="EN-US"><span lang="EN-US">科技大擂台</span></span></a> commented: </span></i></p><div><p><span lang="EN"><a href="https://speech.nchc.org.tw/cjlin" rel="nofollow%20noopener%20noreferrer nofollow noopener noreferrer" target="_blank">@cjlin</a> </span></p><p><span lang="EN">12/26 1800 </span>環境封閉直到賽後，正式比賽將於封閉存取之環境下進行，主辦單位不主動採取任何方式介入並啓動相關程式，請參賽團隊以自動化排程之機制完成二場正式賽。如有特殊狀況，主辦單位將會主動通知團隊<span lang="EN"></span></p><p>結果將於比賽後，擇期公布<span lang="EN"></span></p></div></div><div style="margin-top:7.5pt"><p><span style="color:#777777">—<span lang="EN"> <br><a href="https://speech.nchc.org.tw/fgc/2020_fgc_forum/issues/40#note_330" rel="nofollow%20noopener%20noreferrer nofollow noopener noreferrer" target="_blank">View it on GitLab</a>. <br>You're receiving this email because of your account on speech.nchc.org.tw. If you'd like to receive fewer emails, you can <a href="https://speech.nchc.org.tw/sent_notifications/e87f5b0c792b3477d423bc515657a165/unsubscribe" rel="nofollow%20noopener%20noreferrer nofollow noopener noreferrer" target="_blank">unsubscribe</a> from this thread or adjust your notification settings. </span></span></p></div></div></div></div><br></div></div></body></html>