<div dir="ltr"><div class="gmail_extra"><div class="gmail_quote"><div>talk starts in half an hour at GHC-7101.</div><div><br></div><div>waleed<br></div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><span style="font-size:12.8px">Please join us for the next CL+NLP lunch</span><span style="font-size:12.8px"> at <b>11am on Monday Oct 26th at 7101</b>,</span><br style="font-size:12.8px"><span style="font-size:12.8px">where Jiang Guo will be speaking about </span><span style="font-size:12.8px">Cross-lingual Transfer Parsing</span><span style="font-size:12.8px">. </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 style="font-size:12.8px"><br style="font-size:12.8px"><span style="font-size:12.8px">To arrange meetings with Jiang, please see the following document.</span></div><div style="font-size:12.8px"><span style="font-size:12.8px">(<a href="https://docs.google.com/document/d/1i4s181AWQGY1SJup76BZGgsjpquAH2ZrVe7tHWISPYc/edit" target="_blank">https://docs.google.com/document/d/1i4s181AWQGY1SJup76BZGgsjpquAH2ZrVe7tHWISPYc/edit</a>)</span><br><br style="font-size:12.8px"><br>-----------------------------------------<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">Monday, Oct 26th at 11:00am</span><br style="font-size:12.8px"><span style="font-size:12.8px">GHC 7101</span></b><br style="font-size:12.8px"><br style="font-size:12.8px"><span style="font-size:12.8px">Speaker: Jiang Guo, Johns Hopkins University</span><br style="font-size:12.8px"><br style="font-size:12.8px"><span style="font-size:12.8px">[TITLE]</span><br style="font-size:12.8px">Representation Learning for Cross-lingual Transfer Parsing<br><br style="font-size:12.8px"><span style="font-size:12.8px">[ABSTRACT]</span></div><div style="font-size:12.8px">Cross-lingual model transfer has been a promising approach for inducing dependency parsers for low-resource languages where annotated treebanks are not available. The major obstacles for the model transfer approach are two-fold:<p>1. Lexical features are not directly transferable across languages.</p><p>2. Target language-specific syntactic structures are difficult to be recovered.</p><p>In this talk, I will provide a representation learning framework to address these challenges. By evaluating on the Google universal dependency treebanks (v2.0), our best models yield an absolute improvement of 6.53% in averaged labeled attachment score, as compared with delexicalized multi-source transfer models. We also significantly outperform the state-of-the-art transfer system proposed most recently.</p><br style="font-size:12.8px"><br style="font-size:12.8px">[SHORT BIO]</div><div style="font-size:12.8px">Jiang Guo is a joint Ph.D student at Johns Hopkins University and at Harbin Institute of Technology. His research interests are in the areas of natural language processing, machine learning, with special interests on distributed representation learning and its applications on NLP tasks (mostly structure prediction problems). His long-term goal is developing efficient and effective algorithms and softwares for NLP and machine learning applications.</div><div style="font-size:12.8px"><br>-----------------------------------------<br></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 17th Nov. 12:00-13:00 by Ndapa Nakashole.</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 class="gmail_extra"><br></div></div></blockquote></div>
</div></div>