<div dir="ltr">reminder: in 30 minutes<div class="gmail_extra"><br><div class="gmail_quote">On Wed, Nov 13, 2013 at 4:14 PM, Dani Yogatama <span dir="ltr"><<a href="mailto:dyogatama@cs.cmu.edu" target="_blank">dyogatama@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><b style="font-family:arial,sans-serif;font-size:13px">CL+NLP Lunch </b><font face="arial, sans-serif" style="font-family:arial,sans-serif;font-size:13px">(</font><font color="#1155cc" face="arial, sans-serif" style="font-family:arial,sans-serif;font-size:13px"><u><a href="http://www.cs.cmu.edu/~nlp-lunch/" target="_blank">http://www.cs.cmu.edu/~<span style="background-color:rgb(255,255,204);color:rgb(34,34,34)">nlp</span>-<span style="background-color:rgb(255,255,204);color:rgb(34,34,34)">lunch</span>/</a></u></font><font face="arial, sans-serif" style="font-family:arial,sans-serif;font-size:13px">)</font><br style="font-family:arial,sans-serif;font-size:13px">
<b style="font-family:arial,sans-serif;font-size:13px">Speaker</b><font face="arial, sans-serif" style="font-family:arial,sans-serif;font-size:13px">: </font><span style="font-family:arial,sans-serif;font-size:13px">Vinodkumar Prabhakaran</span><font face="arial, sans-serif" style="font-family:arial,sans-serif;font-size:13px">, </font><span style="font-family:arial,sans-serif;font-size:13px">Columbia University</span><br style="font-family:arial,sans-serif;font-size:13px">
<b style="font-family:arial,sans-serif;font-size:13px">Date</b><font face="arial, sans-serif" style="font-family:arial,sans-serif;font-size:13px">: Tuesday, November 19, 2013</font><br style="font-family:arial,sans-serif;font-size:13px">
<b style="font-family:arial,sans-serif;font-size:13px">Time</b><font face="arial, sans-serif" style="font-family:arial,sans-serif;font-size:13px">: 12:30pm <b>(note: 12.30pm not at noon)</b></font><br style="font-family:arial,sans-serif;font-size:13px">
<b style="font-family:arial,sans-serif;font-size:13px">Venue</b><font face="arial, sans-serif" style="font-family:arial,sans-serif;font-size:13px">: GHC 4405</font><span style="font-family:arial,sans-serif;font-size:13px"><br>
</span></div><span style="font-family:arial,sans-serif;font-size:13px"><div><span style="font-family:arial,sans-serif;font-size:13px"><br></span></div><b>Title:</b> Manifestations of Social Power in Interactions</span><br style="font-family:arial,sans-serif;font-size:13px">
<br style="font-family:arial,sans-serif;font-size:13px"><span style="font-family:arial,sans-serif;font-size:13px"><b>Abstract:</b> In this talk, I will present the study on how social power </span><span style="font-family:arial,sans-serif;font-size:13px">relations affect the way people interact with one another in both</span><br style="font-family:arial,sans-serif;font-size:13px">
<span style="font-family:arial,sans-serif;font-size:13px">online and offline settings and how we can use statistical machine</span><br style="font-family:arial,sans-serif;font-size:13px">
<span style="font-family:arial,sans-serif;font-size:13px">learning techniques to detect these power relations automatically. The</span><br style="font-family:arial,sans-serif;font-size:13px"><span style="font-family:arial,sans-serif;font-size:13px">talk will cover studies on two different domains — A) Enron email</span><br style="font-family:arial,sans-serif;font-size:13px">
<span style="font-family:arial,sans-serif;font-size:13px">corpus (written, task-oriented) and B) 2012 Republican Presidential</span><br style="font-family:arial,sans-serif;font-size:13px"><span style="font-family:arial,sans-serif;font-size:13px">Primary debates (spoken, persuasive). In part A, we explored four</span><br style="font-family:arial,sans-serif;font-size:13px">
<span style="font-family:arial,sans-serif;font-size:13px">different types of power — influence, hierarchical power, situational</span><br style="font-family:arial,sans-serif;font-size:13px"><span style="font-family:arial,sans-serif;font-size:13px">power, and power over communication — within an organizational</span><br style="font-family:arial,sans-serif;font-size:13px">
<span style="font-family:arial,sans-serif;font-size:13px">setting. We found that these four types of power i) manifest in the</span><br style="font-family:arial,sans-serif;font-size:13px"><span style="font-family:arial,sans-serif;font-size:13px">structure of the dialog, ii) are different in the ways they manifest</span><br style="font-family:arial,sans-serif;font-size:13px">
<span style="font-family:arial,sans-serif;font-size:13px">in dialog and iii) can be predicted using automatic means with</span><br style="font-family:arial,sans-serif;font-size:13px"><span style="font-family:arial,sans-serif;font-size:13px">reasonable performance. In part B, the presidential primary debates,</span><br style="font-family:arial,sans-serif;font-size:13px">
<span style="font-family:arial,sans-serif;font-size:13px">we modeled power based on the candidates’ relative position in the</span><br style="font-family:arial,sans-serif;font-size:13px"><span style="font-family:arial,sans-serif;font-size:13px">recent polls released prior to each debate. We found that a</span><br style="font-family:arial,sans-serif;font-size:13px">
<span style="font-family:arial,sans-serif;font-size:13px">candidate’s power affects the way they interact with others in the</span><br style="font-family:arial,sans-serif;font-size:13px"><span style="font-family:arial,sans-serif;font-size:13px">debate as well as the way others interact with them. I will also</span><br style="font-family:arial,sans-serif;font-size:13px">
<span style="font-family:arial,sans-serif;font-size:13px">present an automatic power ranker system to rank candidates in terms</span><br style="font-family:arial,sans-serif;font-size:13px"><span style="font-family:arial,sans-serif;font-size:13px">of their relative power based on linguistic and structural features.</span><br style="font-family:arial,sans-serif;font-size:13px">
<br style="font-family:arial,sans-serif;font-size:13px"><span style="font-family:arial,sans-serif;font-size:13px"><b>Bio:</b> Vinodkumar Prabhakaran is a 4th year PhD student working under</span><br style="font-family:arial,sans-serif;font-size:13px">
<span style="font-family:arial,sans-serif;font-size:13px">the supervision of Dr. Owen Rambow at the Center for Computational</span><br style="font-family:arial,sans-serif;font-size:13px"><span style="font-family:arial,sans-serif;font-size:13px">Learning Systems (CCLS). His research focuses on statistical machine</span><br style="font-family:arial,sans-serif;font-size:13px">
<span style="font-family:arial,sans-serif;font-size:13px">learning techniques for NLP and spans across different areas within</span><br style="font-family:arial,sans-serif;font-size:13px"><span style="font-family:arial,sans-serif;font-size:13px">NLP such as computational sociolinguistics, semantic analysis and</span><br style="font-family:arial,sans-serif;font-size:13px">
<span style="font-family:arial,sans-serif;font-size:13px">biomedical information extraction. His thesis focuses on analyzing</span><br style="font-family:arial,sans-serif;font-size:13px"><span style="font-family:arial,sans-serif;font-size:13px">social interactions to detect social power relations between</span><br style="font-family:arial,sans-serif;font-size:13px">
<span style="font-family:arial,sans-serif;font-size:13px">interactants, across various type of power, genres and domains. His</span><br style="font-family:arial,sans-serif;font-size:13px"><span style="font-family:arial,sans-serif;font-size:13px">work has been published at various international venues such as WWW,</span><br style="font-family:arial,sans-serif;font-size:13px">
<span style="font-family:arial,sans-serif;font-size:13px">NAACL, COLING, IJCNLP and ECAI.</span><br></div>
</blockquote></div><br></div></div>