<div dir="ltr"><div dir="ltr"><div class="gmail_default" style="font-size:small"><div class="gmail_default"><div><div style="color:rgb(80,0,80)"><font face="verdana, sans-serif" size="4"><span style="background-color:rgb(207,226,243)"><b>Thesis Defense: Lifu Tu, TTIC</b></span></font><br></div><div style="color:rgb(80,0,80);font-family:arial,helvetica,sans-serif"><br></div><font face="arial, sans-serif" color="#000000"><b>When:</b><b> </b> Thur<span style="border-bottom:1px dashed rgb(204,204,204)">sday<b style="text-decoration-line:underline">,</b> May 27th at <b style="background-color:rgb(255,255,0)">10:00 am CT</b></span></font></div><div><span style="border-bottom:1px dashed rgb(204,204,204)"><font face="arial, sans-serif" color="#000000"><br></font></span></div><div><font face="arial, sans-serif" color="#000000"><b>Where:</b> <b><i> </i><a href="https://uchicago.zoom.us/j/93121868587?pwd=NFRkOWZuZ2xuVWRQNkVYSHVJYVpBdz09" target="_blank">Join virtually here</a></b></font></div><div><span style="border-bottom:1px dashed rgb(204,204,204)"><font face="arial, sans-serif" color="#000000"><br></font></span></div><div><font face="arial, sans-serif" color="#000000"><b>Who: </b> Lifu Tu, TTIC</font></div><div><font color="#000000"><br></font></div><div><div><font face="arial, sans-serif" color="#000000"><b>Title: </b>Learning Energy-Based Approximate Inference Networks for Structured Applications in NLP</font></div><font face="arial, sans-serif" color="#000000"><br></font><div><div><font face="arial, sans-serif"><font color="#000000"><b>Abstract: </b></font>Researchers are increasingly applying deep representation learning to these problems, but the structured component of these approaches is usually quite simplistic. However, this may have substantially lower accuracy than an approach that models the interactions between the structured outputs. Due to the exponentially large space of candidate outputs, it is computational challenging to jointly predict all components of the structured outputs. During my Ph.D., I work on how to model complex structured outputs with energy functions and better approximate inference for structured tasks. In my work, we use a neural network trained to approximate structured argmax inference with respect to energy functions. This "energy-based inference network" outputs continuous values that we treat as the output structure. In our method, the time complexity for the inference is linear with the label set size. “energy-based Inference networks” achieve a better speed/accuracy/search error trade-off than gradient descent, while also being faster than exact inference at similar accuracy levels. We also design a margin-based method that jointly learns energy function and inference networks. I have applied the method on several NLP tasks, including multi-label classification, part-of-speech tagging, named entity recognition, semantic role labeling, and non-autoregressive machine translation.</font></div></div></div><div><font face="arial, sans-serif"><br></font></div><font face="arial, sans-serif"><b><font color="#000000">Thesis Advisor:</font></b><font color="#500050"> </font><a href="mailto:kgimpel@ttic.edu" target="_blank"><b><font color="#0000ff">Kevin Gimpel</font></b></a></font></div><div class="gmail_default"><font face="arial, sans-serif"><br></font></div><div class="gmail_default"><br></div><div class="gmail_default"><font face="arial, sans-serif"><span style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap">Join Zoom Meeting
</span><a href="https://www.google.com/url?q=https://uchicago.zoom.us/j/93121868587?pwd%3DNFRkOWZuZ2xuVWRQNkVYSHVJYVpBdz09&sa=D&source=calendar&ust=1621298635898000&usg=AOvVaw067Gwb-OCTKfwsWBK4-z4i" target="_blank" style="color:rgb(26,115,232);letter-spacing:0.2px;white-space:pre-wrap"><b><font size="1">https://uchicago.zoom.us/j/93121868587?pwd=NFRkOWZuZ2xuVWRQNkVYSHVJYVpBdz09</font></b></a><span style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap"><font size="1">
</font>
Meeting ID: 931 2186 8587
Passcode: 784939</span></font><br></div><div class="gmail_default"><font color="#500050" face="arial, sans-serif" style="color:rgb(80,0,80)"><br></font><div style="color:rgb(80,0,80)"><font face="arial, sans-serif">******************************************************************************************************</font></div><br class="gmail-Apple-interchange-newline"></div><div class="gmail_default"><br></div><div class="gmail_default"><br></div></div><div><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div dir="ltr"><div dir="ltr"><div dir="ltr"><div dir="ltr"><div dir="ltr"><div dir="ltr"><font face="arial, helvetica, sans-serif">Mary C. Marre</font><div><font face="arial, helvetica, sans-serif">Faculty Administrative Support</font></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6"><b>Toyota Technological Institute</b></font></i></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6">6045 S. Kenwood Avenue</font></i></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6">Chicago, IL 60637</font></i></div><div><b><i><a href="mailto:mmarre@ttic.edu" target="_blank"><font face="arial, helvetica, sans-serif">mmarre@ttic.edu</font></a></i></b><br></div></div></div></div></div></div></div></div></div></div><br></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Thu, May 20, 2021 at 1:00 PM Mary Marre <<a href="mailto:mmarre@ttic.edu">mmarre@ttic.edu</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div dir="ltr"><div style="font-size:small"><div><div><div style="color:rgb(80,0,80)"><font face="verdana, sans-serif" size="4"><span style="background-color:rgb(207,226,243)"><b>Thesis Defense: Lifu Tu, TTIC</b></span></font><br></div><div style="color:rgb(80,0,80);font-family:arial,helvetica,sans-serif"><br></div><font face="arial, sans-serif" color="#000000"><b>When:</b><b> </b> Thur<span style="border-bottom:1px dashed rgb(204,204,204)">sday<b style="text-decoration-line:underline">,</b> May 27th at <b style="background-color:rgb(255,255,0)">10:00 am CT</b></span></font></div><div><span style="border-bottom:1px dashed rgb(204,204,204)"><font face="arial, sans-serif" color="#000000"><br></font></span></div><div><font face="arial, sans-serif" color="#000000"><b>Where:</b> <b><i> </i><a href="https://uchicago.zoom.us/j/93121868587?pwd=NFRkOWZuZ2xuVWRQNkVYSHVJYVpBdz09" target="_blank">Join virtually here</a></b></font></div><div><span style="border-bottom:1px dashed rgb(204,204,204)"><font face="arial, sans-serif" color="#000000"><br></font></span></div><div><font face="arial, sans-serif" color="#000000"><b>Who: </b> Lifu Tu, TTIC</font></div><div><font color="#000000"><br></font></div><div><div><font face="arial, sans-serif" color="#000000"><b>Title: </b>Learning Energy-Based Approximate Inference Networks for Structured Applications in NLP</font></div><font face="arial, sans-serif" color="#000000"><br></font><div><div><font face="arial, sans-serif"><font color="#000000"><b>Abstract: </b></font>Researchers are increasingly applying deep representation learning to these problems, but the structured component of these approaches is usually quite simplistic. However, this may have substantially lower accuracy than an approach that models the interactions between the structured outputs. Due to the exponentially large space of candidate outputs, it is computational challenging to jointly predict all components of the structured outputs. During my Ph.D., I work on how to model complex structured outputs with energy functions and better approximate inference for structured tasks. In my work, we use a neural network trained to approximate structured argmax inference with respect to energy functions. This "energy-based inference network" outputs continuous values that we treat as the output structure. In our method, the time complexity for the inference is linear with the label set size. “energy-based Inference networks” achieve a better speed/accuracy/search error trade-off than gradient descent, while also being faster than exact inference at similar accuracy levels. We also design a margin-based method that jointly learns energy function and inference networks. I have applied the method on several NLP tasks, including multi-label classification, part-of-speech tagging, named entity recognition, semantic role labeling, and non-autoregressive machine translation.</font></div></div></div><div><font face="arial, sans-serif"><br></font></div><font face="arial, sans-serif"><b><font color="#000000">Thesis Advisor:</font></b><font color="#500050"> </font><a href="mailto:kgimpel@ttic.edu" target="_blank"><b><font color="#0000ff">Kevin Gimpel</font></b></a></font></div><div><font face="arial, sans-serif"><br></font></div><div><br></div><div><font face="arial, sans-serif"><span style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap">Join Zoom Meeting
</span><a href="https://www.google.com/url?q=https://uchicago.zoom.us/j/93121868587?pwd%3DNFRkOWZuZ2xuVWRQNkVYSHVJYVpBdz09&sa=D&source=calendar&ust=1621298635898000&usg=AOvVaw067Gwb-OCTKfwsWBK4-z4i" style="color:rgb(26,115,232);letter-spacing:0.2px;white-space:pre-wrap" target="_blank"><b><font size="1">https://uchicago.zoom.us/j/93121868587?pwd=NFRkOWZuZ2xuVWRQNkVYSHVJYVpBdz09</font></b></a><span style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap"><font size="1">
</font>
Meeting ID: 931 2186 8587
Passcode: 784939</span></font><br></div><div><font color="#500050" face="arial, sans-serif" style="color:rgb(80,0,80)"><br></font><div style="color:rgb(80,0,80)"><font face="arial, sans-serif">******************************************************************************************************</font></div><div style="color:rgb(80,0,80)"><font face="arial, sans-serif"><br></font></div><br></div></div><div><div dir="ltr"><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><font face="arial, helvetica, sans-serif">Mary C. Marre</font><div><font face="arial, helvetica, sans-serif">Faculty Administrative Support</font></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6"><b>Toyota Technological Institute</b></font></i></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6">6045 S. Kenwood Avenue</font></i></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6">Room 517</font></i></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6">Chicago, IL 60637</font></i></div><div><i><font face="arial, helvetica, sans-serif">p:(773) 834-1757</font></i></div><div><i><font face="arial, helvetica, sans-serif">f: (773) 357-6970</font></i></div><div><b><i><a href="mailto:mmarre@ttic.edu" target="_blank"><font face="arial, helvetica, sans-serif">mmarre@ttic.edu</font></a></i></b></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div><br></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Thu, May 13, 2021 at 5:20 PM Mary Marre <<a href="mailto:mmarre@ttic.edu" target="_blank">mmarre@ttic.edu</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div><div><div style="font-size:small"><div style="color:rgb(80,0,80)"><font face="verdana, sans-serif" size="4"><span style="background-color:rgb(207,226,243)"><b>Thesis Defense: Lifu Tu, TTIC</b></span></font><br></div><div style="color:rgb(80,0,80);font-family:arial,helvetica,sans-serif"><br></div><font face="arial, sans-serif" color="#000000"><b>When:</b><b> </b> Thur<span style="border-bottom:1px dashed rgb(204,204,204)">sday<b style="text-decoration-line:underline">,</b> May 27th at <b style="background-color:rgb(255,255,0)">10:00 am CT</b></span></font></div><div style="font-size:small"><span style="border-bottom:1px dashed rgb(204,204,204)"><font face="arial, sans-serif" color="#000000"><br></font></span></div><div style="font-size:small"><font face="arial, sans-serif" color="#000000"><b>Where:</b> <b><i> </i><a href="https://uchicago.zoom.us/j/93121868587?pwd=NFRkOWZuZ2xuVWRQNkVYSHVJYVpBdz09" target="_blank">Join virtually here</a></b></font></div><div style="font-size:small"><span style="border-bottom:1px dashed rgb(204,204,204)"><font face="arial, sans-serif" color="#000000"><br></font></span></div><div style="font-size:small"><font face="arial, sans-serif" color="#000000"><b>Who: </b> Lifu Tu, TTIC</font></div><div style="font-size:small"><font color="#000000"><br></font></div><div><div><font face="arial, sans-serif" color="#000000"><b>Title: </b>Learning Energy-Based Approximate Inference Networks for Structured Applications in NLP</font></div><font face="arial, sans-serif" color="#000000"><br></font><div><div><font face="arial, sans-serif"><font color="#000000"><b>Abstract: </b></font>Researchers are increasingly applying deep representation learning to these problems, but the structured component of these approaches is usually quite simplistic. However, this may have substantially lower accuracy than an approach that models the interactions between the structured outputs. Due to the exponentially large space of candidate outputs, it is computational challenging to jointly predict all components of the structured outputs. During my Ph.D., I work on how to model complex structured outputs with energy functions and better approximate inference for structured tasks. In my work, we use a neural network trained to approximate structured argmax inference with respect to energy functions. This "energy-based inference network" outputs continuous values that we treat as the output structure. In our method, the time complexity for the inference is linear with the label set size. “energy-based Inference networks” achieve a better speed/accuracy/search error trade-off than gradient descent, while also being faster than exact inference at similar accuracy levels. We also design a margin-based method that jointly learns energy function and inference networks. I have applied the method on several NLP tasks, including multi-label classification, part-of-speech tagging, named entity recognition, semantic role labeling, and non-autoregressive machine translation.</font></div></div></div><div><font face="arial, sans-serif"><br></font></div><font face="arial, sans-serif"><b><font color="#000000">Thesis Advisor:</font></b><font color="#500050"> </font><a href="mailto:kgimpel@ttic.edu" target="_blank"><b><font color="#0000ff">Kevin Gimpel</font></b></a></font></div><div><font face="arial, sans-serif"><br></font></div><div style="font-size:small"><br></div><div><font face="arial, sans-serif"><span style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap">Join Zoom Meeting
</span><a href="https://www.google.com/url?q=https://uchicago.zoom.us/j/93121868587?pwd%3DNFRkOWZuZ2xuVWRQNkVYSHVJYVpBdz09&sa=D&source=calendar&ust=1621298635898000&usg=AOvVaw067Gwb-OCTKfwsWBK4-z4i" style="color:rgb(26,115,232);letter-spacing:0.2px;white-space:pre-wrap" target="_blank"><b><font size="1">https://uchicago.zoom.us/j/93121868587?pwd=NFRkOWZuZ2xuVWRQNkVYSHVJYVpBdz09</font></b></a><span style="color:rgb(60,64,67);letter-spacing:0.2px;white-space:pre-wrap"><font size="1">
</font>
Meeting ID: 931 2186 8587
Passcode: 784939</span></font><br></div><div style="font-size:small"><font color="#500050" face="arial, sans-serif" style="color:rgb(80,0,80)"><br></font><div style="color:rgb(80,0,80)"><font face="arial, sans-serif">******************************************************************************************************</font></div><div style="color:rgb(80,0,80)"><font face="arial, sans-serif"><br></font></div><div style="color:rgb(80,0,80)"><font face="arial, sans-serif"><br></font></div><div style="color:rgb(80,0,80)"><font face="arial, sans-serif"><br></font></div><div style="color:rgb(80,0,80)"><font face="arial, sans-serif"><br></font></div></div></div><div><div dir="ltr"><div dir="ltr"><div dir="ltr"><div dir="ltr"><div dir="ltr"><div dir="ltr"><div dir="ltr"><div dir="ltr"><font face="arial, helvetica, sans-serif" size="1">Mary C. Marre</font><div><font face="arial, helvetica, sans-serif" size="1">Faculty Administrative Support</font></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6" size="1"><b>Toyota Technological Institute</b></font></i></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6" size="1">6045 S. Kenwood Avenue</font></i></div><div><font size="1"><i><font face="arial, helvetica, sans-serif" color="#3d85c6">Chicago, IL 60637</font></i><br></font></div><div><b><i><a href="mailto:mmarre@ttic.edu" target="_blank"><font face="arial, helvetica, sans-serif" size="1">mmarre@ttic.edu</font></a></i></b><br></div></div></div></div></div></div></div></div></div></div></div>
</blockquote></div></div>
</blockquote></div></div>