<div dir="ltr">A gentle reminder that the talk will be tomorrow (Tuesday) noon in <b>GHC 6115.</b></div><div class="gmail_extra"><br><div class="gmail_quote">On Sun, May 6, 2018 at 2:51 PM, Adams Wei Yu <span dir="ltr"><<a href="mailto:weiyu@cs.cmu.edu" target="_blank">weiyu@cs.cmu.edu</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div style="color:rgb(34,34,34);font-family:arial,sans-serif;font-size:12.8px;font-style:normal;font-variant-ligatures:normal;font-variant-caps:normal;font-weight:400;letter-spacing:normal;text-align:start;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;text-decoration-style:initial;text-decoration-color:initial;background-color:rgb(255,255,255)">Dear faculty and students,</div><div style="color:rgb(34,34,34);font-family:arial,sans-serif;font-size:12.8px;font-style:normal;font-variant-ligatures:normal;font-variant-caps:normal;font-weight:400;letter-spacing:normal;text-align:start;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;text-decoration-style:initial;text-decoration-color:initial;background-color:rgb(255,255,255)"><br></div><div style="color:rgb(34,34,34);font-family:arial,sans-serif;font-size:12.8px;font-style:normal;font-variant-ligatures:normal;font-variant-caps:normal;letter-spacing:normal;text-align:start;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;text-decoration-style:initial;text-decoration-color:initial;background-color:rgb(255,255,255)"><span style="font-weight:400">We look forward to seeing you next Tuesday, May 08, at noon in </span><b>GHC 6115</b><b style="font-weight:400"> </b>for AI Seminar sponsored by Apple. To learn more about the seminar series, please visit the AI Seminar <a href="http://www.cs.cmu.edu/~aiseminar/" style="font-weight:400;color:rgb(17,85,204)" target="_blank">webpage</a>.</div><div style="color:rgb(34,34,34);font-family:arial,sans-serif;font-size:12.8px;font-style:normal;font-variant-ligatures:normal;font-variant-caps:normal;font-weight:400;letter-spacing:normal;text-align:start;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;text-decoration-style:initial;text-decoration-color:initial;background-color:rgb(255,255,255)"><br></div><div style="color:rgb(34,34,34);font-family:arial,sans-serif;font-size:12.8px;font-style:normal;font-variant-ligatures:normal;font-variant-caps:normal;font-weight:400;letter-spacing:normal;text-align:start;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;text-decoration-style:initial;text-decoration-color:initial;background-color:rgb(255,255,255)"><span style="color:rgb(34,34,34);font-family:arial,sans-serif;font-size:12.8px;font-style:normal;font-variant-ligatures:normal;font-variant-caps:normal;font-weight:400;letter-spacing:normal;text-transform:none;white-space:normal;word-spacing:0px">On Tuesday, <a href="http://www.cs.cmu.edu/~weiyu/" target="_blank">Adams Wei Yu</a></span><span style="font-size:12.8px"> will give the following talk: </span></div><div style="color:rgb(34,34,34);font-family:arial,sans-serif;font-size:12.8px;font-style:normal;font-variant-ligatures:normal;font-variant-caps:normal;font-weight:400;letter-spacing:normal;text-align:start;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;text-decoration-style:initial;text-decoration-color:initial;background-color:rgb(255,255,255)"><br></div><div style="text-align:start;text-indent:0px;text-decoration-style:initial;text-decoration-color:initial;background-color:rgb(255,255,255)"><div><span style="color:rgb(34,34,34);font-family:arial,sans-serif;font-size:12.8px;font-style:normal;font-variant-ligatures:normal;font-variant-caps:normal;font-weight:400;letter-spacing:normal;text-transform:none;white-space:normal;word-spacing:0px">Title: </span><span style="font-size:12.8px">Efficient and Effective Models for Machine Reading Comprehension</span></div><div style="color:rgb(34,34,34);font-family:arial,sans-serif;font-size:12.8px;font-style:normal;font-variant-ligatures:normal;font-variant-caps:normal;font-weight:400;letter-spacing:normal;text-transform:none;white-space:normal;word-spacing:0px"><span style="color:rgb(34,34,34);font-family:arial,sans-serif;font-size:12.8px;font-style:normal;font-variant-ligatures:normal;font-variant-caps:normal;font-weight:400;letter-spacing:normal;text-transform:none;white-space:normal;word-spacing:0px"><br></span></div><div><div><div><span style="font-size:12.8px">Abstract: </span></div><div><span style="font-size:12.8px"><br></span></div><div><span style="font-size:12.8px">Machine reading comprehension has attracted lots of attentions in the AI, ML and NLP communities. In this talk, I will introduce two efficient and effective models to approach this task. </span></div><div><span style="font-size:12.8px"><br></span></div><div><span style="font-size:12.8px">Firstly, I will propose a model, LSTM-Jump, that can skip unimportant information in sequential data, mimicking the skimming behavior of human reading. Trained with an efficient reinforcement learning algorithm, this model can be several times faster than a vanilla LSTM in inference time. </span></div><div><span style="font-size:12.8px"><br></span></div><div><span style="font-size:12.8px">Then I will introduce a sequence encoding method that discards recurrent networks, which thus fully supports parallel training and inference. Based on this technique, a new question-answering model, QANet, is proposed. Combined with data augmentation approach via backtranslation, this model achieves No.1 performance in the competitive Stanford Question and Answer Dataset (SQuAD), while being times faster than the prevalent models. Notably, the exact match score of QANet has exceeded human performance.</span></div><div><span style="font-size:12.8px"><br></span></div><div><span style="font-size:12.8px">The talk is based on the following two works: </span></div><div><span style="font-size:12.8px">1. <a href="http://aclweb.org/anthology/P17-1172" target="_blank">http://aclweb.org/anthology/<wbr>P17-1172</a></span></div><div><span style="font-size:12.8px">2. <a href="https://arxiv.org/pdf/1804.09541.pdf" target="_blank">https://arxiv.org/pdf/1804.<wbr>09541.pdf</a></span></div></div></div></div><div class="m_2876379798121797722gmail-yj6qo" style="color:rgb(34,34,34);font-family:arial,sans-serif;font-size:12.8px;font-style:normal;font-variant-ligatures:normal;font-variant-caps:normal;font-weight:400;letter-spacing:normal;text-align:start;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;background-color:rgb(255,255,255);text-decoration-style:initial;text-decoration-color:initial"></div><div><br></div><div><br></div><div><br></div><div><br></div><div><br></div><div><br></div></div>
</blockquote></div><br></div>