<div dir="ltr"><div class="gmail_extra" style="font-size:14px"><span style="font-size:12.8px">This is a reminder for <span class="">NLP</span> lunh talk today!</span></div><div class="gmail_extra" style="font-size:14px"><span style="font-size:12.8px"><br></span></div><div class="gmail_extra" style="font-size:14px"><span style="font-size:12.8px">Please join us for the next CL+<span class="">NLP</span> <span class="">lunch</span></span><span style="font-size:12.8px"> at <b>13am </b></span><span style="font-size:12.8px"><b>at </b></span><b style="font-size:12.8px">8102</b><span style="font-size:12.8px">,</span><br style="font-size:12.8px"><span style="font-size:12.8px">where Ndapa Nakashole will be speaking about Knowledge Graph. </span><div style="font-size:12.8px"><span style="font-size:12.8px"><span class="">Lunch</span></span><span style="font-size:12.8px"> will be </span><span style="font-size:12.8px">provided.</span><br></div><div style="font-size:12.8px"><span style="font-size:12.8px"><br></span></div><div style="font-size:12.8px"><span style="font-size:12.8px">We got some requests for recording, but u</span><span style="font-size:12.8px">nfortunately we cannot record the talk this time. L</span><span style="font-size:12.8px">et me figure out how to share the talk to students in conferences and in SV campus.</span></div><div><br><span style="font-size:12.8px">------------------------------</span><span style="font-size:12.8px">-----------</span><br style="font-size:12.8px"><span style="font-size:12.8px">ML</span><span style="font-size:12.8px">+<span class="">NLP</span> </span><span style="font-size:12.8px"><span class="">lunch</span></span><br style="font-size:12.8px"><b><span style="font-size:12.8px">Tuesday Nov 17th at 13:00 - 14:00</span><br style="font-size:12.8px"></b><span style="font-size:12.8px"><b>GHC 8102</b></span><br style="font-size:12.8px"><br style="font-size:12.8px">The Knowledge Graph Extraction Virtuous Circle</div><div><div><br></div><div>Knowledge graphs such a NELL, Freebase, and YAGO have accumulated large amounts of beliefs about real world entities using machine reading methods. </div><div>Current machine readers have been successful at populating such knowledge graphs by means of pattern detection — a shallow way of machine reading</div><div>which leverages the redundancy of large corpora to capture language patterns. However, machine readers still lack the ability to fully understand language. </div><div>In the pursuit of the much harder goal of language comprehension, knowledge graphs present an opportunity for a virtuous circle: the accumulated knowledge</div><div>can be used to improve machine readers; in turn, advanced reading methods can be used to populate knowledge graphs with beliefs expressed using complex and potentially ambiguous language. In this talk, I will elaborate on this virtuous circle, starting with methods for building knowledge graphs, followed by results on using them for machine reading.</div></div><div><br></div><div><br></div><div><div>Bio:</div><div>Ndapa Nakashole is a postdoctoral fellow in the Machine Learning Department at Carnegie Mellon University.</div><div>She holds a B.Sc and an M.Sc from the University of Cape Town, South Africa and a PhD from the Max Planck Institute for Informatics and Saarland University, Germany. </div></div><div></div><div style="font-size:12.8px">-----------------------------------------<br></div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px">Best regards,</div><div style="font-size:12.8px">Kazuya</div><div><br></div></div><div class="gmail_extra"><br><div class="gmail_quote">On Mon, Nov 16, 2015 at 11:03 AM, Kazuya Kawakami <span dir="ltr"><<a href="mailto:kkawakam@andrew.cmu.edu" target="_blank">kkawakam@andrew.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 class="gmail_extra" style="font-size:14px"><span style="font-size:12.8px">This is a reminder for NLP lunh talk tomorrow.</span></div><div class="gmail_extra" style="font-size:14px"><span style="font-size:12.8px"><br></span></div><div class="gmail_extra" style="font-size:14px"><span style="font-size:12.8px">Please join us for the next CL+NLP lunch</span><span style="font-size:12.8px"> at <b>13am on </b></span><b><span style="font-size:12.8px">Nov</span></b><span style="font-size:12.8px"><b> </b></span><b style="font-size:12.8px"><span style="font-size:12.8px">17th</span></b><span style="font-size:12.8px"><b> at </b></span><b style="font-size:12.8px">8102</b><span style="font-size:12.8px">,</span><br style="font-size:12.8px"><span style="font-size:12.8px">where Ndapa Nakashole will be speaking about Knowledge Graph. </span><div style="font-size:12.8px"><span style="font-size:12.8px">Lunch</span><span style="font-size:12.8px"> will be </span><span style="font-size:12.8px">provided!</span><br></div><div><br><span style="font-size:12.8px">------------------------------</span><span style="font-size:12.8px">-----------</span><br style="font-size:12.8px"><span style="font-size:12.8px">ML</span><span style="font-size:12.8px">+NLP </span><span style="font-size:12.8px">lunch</span><br style="font-size:12.8px"><b><span style="font-size:12.8px">Tuesday Nov 17th at 13:00 - 14:00</span><br style="font-size:12.8px"></b><span style="font-size:12.8px"><b>GHC 8102</b></span><br style="font-size:12.8px"><br style="font-size:12.8px">The Knowledge Graph Extraction Virtuous Circle</div><div><div><br></div><div>Knowledge graphs such a NELL, Freebase, and YAGO have accumulated large amounts of beliefs about real world entities using machine reading methods. </div><div>Current machine readers have been successful at populating such knowledge graphs by means of pattern detection — a shallow way of machine reading</div><div>which leverages the redundancy of large corpora to capture language patterns. However, machine readers still lack the ability to fully understand language. </div><div>In the pursuit of the much harder goal of language comprehension, knowledge graphs present an opportunity for a virtuous circle: the accumulated knowledge</div><div>can be used to improve machine readers; in turn, advanced reading methods can be used to populate knowledge graphs with beliefs expressed using complex and potentially ambiguous language. In this talk, I will elaborate on this virtuous circle, starting with methods for building knowledge graphs, followed by results on using them for machine reading.</div></div><div><br></div><div><br></div><div><div>Bio:</div><div>Ndapa Nakashole is a postdoctoral fellow in the Machine Learning Department at Carnegie Mellon University.</div><div>She holds a B.Sc and an M.Sc from the University of Cape Town, South Africa and a PhD from the Max Planck Institute for Informatics and Saarland University, Germany. </div></div><div></div><div style="font-size:12.8px">-----------------------------------------<br></div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px">Up comming talk will be on <span style="font-size:12.8px">Monday, Nov.23,</span> by <span style="font-size:12.8px">Chu-Ren Huang</span>.</div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px">Best regards,</div><div style="font-size:12.8px">Kazuya</div></div><div class="gmail_extra"><br><div class="gmail_quote">On Mon, Nov 16, 2015 at 11:00 AM, Kazuya Kawakami <span dir="ltr"><<a href="mailto:www.kazuya.kawakami@gmail.com" target="_blank">www.kazuya.kawakami@gmail.com</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 class="gmail_extra"><span style="font-size:12.8px">This is a reminder for NLP lunh talk tomorrow.</span></div><div><div><div class="gmail_extra"><span style="font-size:12.8px"><br></span></div><div class="gmail_extra"><span style="font-size:12.8px">Please join us for the next CL+NLP lunch</span><span style="font-size:12.8px"> at <b>13am on </b></span><b style="font-size:14px"><span style="font-size:12.8px">Nov</span></b><span style="font-size:12.8px"><b> </b></span><b style="font-size:12.8px"><span style="font-size:12.8px">17th</span></b><span style="font-size:12.8px"><b> at </b></span><b style="font-size:12.8px">8102</b><span style="font-size:12.8px">,</span><br style="font-size:12.8px"><span style="font-size:12.8px">where <span>Ndapa</span> Nakashole will be speaking about Knowledge Graph. </span><div style="font-size:12.8px"><span style="font-size:12.8px">Lunch</span><span style="font-size:12.8px"> will be </span><span style="font-size:12.8px">provided!</span><br></div><div style="font-size:14px"><br><span style="font-size:12.8px">------------------------------</span><span style="font-size:12.8px">-----------</span><br style="font-size:12.8px"><span style="font-size:12.8px">ML</span><span style="font-size:12.8px">+NLP </span><span style="font-size:12.8px">lunch</span><br style="font-size:12.8px"><b><span style="font-size:12.8px">Tuesday Nov 17th at 13:00 - 14:00</span><br style="font-size:12.8px"></b><span style="font-size:12.8px"><b>GHC 8102</b></span><br style="font-size:12.8px"><br style="font-size:12.8px">The Knowledge Graph Extraction Virtuous Circle</div><div style="font-size:14px"><div><br></div><div>Knowledge graphs such a NELL, Freebase, and YAGO have accumulated large amounts of beliefs about real world entities using machine reading methods. </div><div>Current machine readers have been successful at populating such knowledge graphs by means of pattern detection — a shallow way of machine reading</div><div>which leverages the redundancy of large corpora to capture language patterns. However, machine readers still lack the ability to fully understand language. </div><div>In the pursuit of the much harder goal of language comprehension, knowledge graphs present an opportunity for a virtuous circle: the accumulated knowledge</div><div>can be used to improve machine readers; in turn, advanced reading methods can be used to populate knowledge graphs with beliefs expressed using complex and potentially ambiguous language. In this talk, I will elaborate on this virtuous circle, starting with methods for building knowledge graphs, followed by results on using them for machine reading.</div></div><div style="font-size:14px"><br></div><div style="font-size:14px"><br></div><div style="font-size:14px"><div>Bio:</div><div><span>Ndapa</span> Nakashole is a postdoctoral fellow in the Machine Learning Department at Carnegie Mellon University.</div><div>She holds a B.Sc and an M.Sc from the University of Cape Town, South Africa and a PhD from the Max Planck Institute for Informatics and Saarland University, Germany. </div></div><div style="font-size:14px"></div><div style="font-size:12.8px">-----------------------------------------<br></div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px">Up comming talk will be on <span style="font-size:12.8px">Monday, Nov.23,</span> by <span style="font-size:12.8px">Chu-Ren Huang</span>.</div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px">Best regards,</div><div style="font-size:12.8px">Kazuya</div></div></div></div></div>
</blockquote></div><br></div></div>
</blockquote></div><br></div></div>