[Theory] Reminder: 5/27 Thesis Defense: Lifu Tu, TTIC

[Mary Marre]

*Thesis Defense: Lifu Tu, TTIC*

*When:*      Thursday*,* May 27th at *10:00 am CT*

*Where:*    * Join virtually here
<https://uchicago.zoom.us/j/93121868587?pwd=NFRkOWZuZ2xuVWRQNkVYSHVJYVpBdz09>*

*Who: *       Lifu Tu, TTIC

*Title:        *Learning Energy-Based Approximate Inference Networks for
Structured Applications in NLP

*Abstract: *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.

*Thesis Advisor:* *Kevin Gimpel* <kgimpel at ttic.edu>


Join Zoom Meeting
*https://uchicago.zoom.us/j/93121868587?pwd=NFRkOWZuZ2xuVWRQNkVYSHVJYVpBdz09*
<https://www.google.com/url?q=https://uchicago.zoom.us/j/93121868587?pwd%3DNFRkOWZuZ2xuVWRQNkVYSHVJYVpBdz09&sa=D&source=calendar&ust=1621298635898000&usg=AOvVaw067Gwb-OCTKfwsWBK4-z4i>
Meeting
ID: 931 2186 8587 Passcode: 784939

******************************************************************************************************



Mary C. Marre
Faculty Administrative Support
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Chicago, IL  60637*
*mmarre at ttic.edu <mmarre at ttic.edu>*


On Thu, May 20, 2021 at 1:00 PM Mary Marre <mmarre at ttic.edu> wrote:

> *Thesis Defense: Lifu Tu, TTIC*
>
> *When:*      Thursday*,* May 27th at *10:00 am CT*
>
> *Where:*    * Join virtually here
> <https://uchicago.zoom.us/j/93121868587?pwd=NFRkOWZuZ2xuVWRQNkVYSHVJYVpBdz09>*
>
> *Who: *       Lifu Tu, TTIC
>
> *Title:        *Learning Energy-Based Approximate Inference Networks for
> Structured Applications in NLP
>
> *Abstract: *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.
>
> *Thesis Advisor:* *Kevin Gimpel* <kgimpel at ttic.edu>
>
>
> Join Zoom Meeting
> *https://uchicago.zoom.us/j/93121868587?pwd=NFRkOWZuZ2xuVWRQNkVYSHVJYVpBdz09*
> <https://www.google.com/url?q=https://uchicago.zoom.us/j/93121868587?pwd%3DNFRkOWZuZ2xuVWRQNkVYSHVJYVpBdz09&sa=D&source=calendar&ust=1621298635898000&usg=AOvVaw067Gwb-OCTKfwsWBK4-z4i> Meeting
> ID: 931 2186 8587 Passcode: 784939
>
>
> ******************************************************************************************************
>
>
> Mary C. Marre
> Faculty Administrative Support
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue*
> *Room 517*
> *Chicago, IL  60637*
> *p:(773) 834-1757*
> *f: (773) 357-6970*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
>
> On Thu, May 13, 2021 at 5:20 PM Mary Marre <mmarre at ttic.edu> wrote:
>
>> *Thesis Defense: Lifu Tu, TTIC*
>>
>> *When:*      Thursday*,* May 27th at *10:00 am CT*
>>
>> *Where:*    * Join virtually here
>> <https://uchicago.zoom.us/j/93121868587?pwd=NFRkOWZuZ2xuVWRQNkVYSHVJYVpBdz09>*
>>
>> *Who: *       Lifu Tu, TTIC
>>
>> *Title:        *Learning Energy-Based Approximate Inference Networks for
>> Structured Applications in NLP
>>
>> *Abstract: *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.
>>
>> *Thesis Advisor:* *Kevin Gimpel* <kgimpel at ttic.edu>
>>
>>
>> Join Zoom Meeting
>> *https://uchicago.zoom.us/j/93121868587?pwd=NFRkOWZuZ2xuVWRQNkVYSHVJYVpBdz09*
>> <https://www.google.com/url?q=https://uchicago.zoom.us/j/93121868587?pwd%3DNFRkOWZuZ2xuVWRQNkVYSHVJYVpBdz09&sa=D&source=calendar&ust=1621298635898000&usg=AOvVaw067Gwb-OCTKfwsWBK4-z4i> Meeting
>> ID: 931 2186 8587 Passcode: 784939
>>
>>
>> ******************************************************************************************************
>>
>>
>>
>>
>> Mary C. Marre
>> Faculty Administrative Support
>> *Toyota Technological Institute*
>> *6045 S. Kenwood Avenue*
>> *Chicago, IL  60637*
>> *mmarre at ttic.edu <mmarre at ttic.edu>*
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20210526/75a9eea8/attachment-0001.html>