[Theory] REMINDER: 3/18 Talks at TTIC: Wenpeng Yin, University of Pennsylvania

[Mary Marre]

When:     Monday, March 18th at *11:00 am*

Where:    TTIC, 6045 S Kenwood Avenue, 5th Floor, Room 526

*Who:*       Wenpeng Yin, University of Pennsylvania


*Title: *Representation Learning in Textual Entailment

*Abstract: *Reasoning is a core approach for humans to gain knowledge. Then
what knowledge can we obtain from reasoning over a textual description? On
the one hand, by a textual description such as “Russia is the largest
country in the world, followed by Canada”, we can infer some “new”
knowledge such as “Canada is the second largest country in the world”,
“Russia is larger than Canada” and “Canada is in top two by size of
territorial area” etc. Here, we approach a “new” knowledge world from the
textual description. On the other hand, we may infer the truth value of a
textual description such as “Zurich is the capital of Switzerland” based on
our existing knowledge world. For example, we may doubt and refute that
textual description by knowledge “Bern is the de facto capital of
Switzerland, referred to by the Swiss as their (e.g. in German)
Bundesstadt, or "federal city"” (Wikipedia). Both scenarios are essentially
a textual entailment problem.


In this talk, I will introduce textual entailment problems and solutions in
different aspects, focusing on the core challenge -- representation
learning. Particularly, how to learn a dynamic representation for the
textual description corresponding to specific tasks and contexts? At last,
 I will discuss some future (ongoing) work for textual entailment, such as
the commonsense entailment, multimodal entailment etc.

Bio: Wenpeng Yin is a postdoctoral researcher in University of
Pennsylvania, working with Prof. Dan Roth in textual entailment and
information extraction. Wenpeng received a Ph.D. degree in 2017 from
University of Munich, Germany. He had an internship in IBM Watson Research
Center in early 2016, and got multiple competitive awards in the past,
including WISE2013 “Best Paper”,  "Baidu Ph.D. Fellowship" in 2014,
"Chinese Government Award for Outstanding Self-financed Ph.D. Students
Abroad" in 2016 and “Area Chair Favorites” paper award in COLING2018. He
serves as the Area Chair for NAACL'2019 and ACL'2019.


Host: Kevin Gimpel <kgimpel at ttic.edu>



Mary C. Marre
Administrative Assistant
*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 Sun, Mar 17, 2019 at 6:08 PM Mary Marre <mmarre at ttic.edu> wrote:

> When:     Monday, March 18th at *11:00 am*
>
> Where:    TTIC, 6045 S Kenwood Avenue, 5th Floor, Room 526
>
> *Who:*       Wenpeng Yin, University of Pennsylvania
>
>
> *Title: *Representation Learning in Textual Entailment
>
> *Abstract: *Reasoning is a core approach for humans to gain knowledge.
> Then what knowledge can we obtain from reasoning over a textual
> description? On the one hand, by a textual description such as “Russia is
> the largest country in the world, followed by Canada”, we can infer some
> “new” knowledge such as “Canada is the second largest country in the
> world”, “Russia is larger than Canada” and “Canada is in top two by size of
> territorial area” etc. Here, we approach a “new” knowledge world from the
> textual description. On the other hand, we may infer the truth value of a
> textual description such as “Zurich is the capital of Switzerland” based on
> our existing knowledge world. For example, we may doubt and refute that
> textual description by knowledge “Bern is the de facto capital of
> Switzerland, referred to by the Swiss as their (e.g. in German)
> Bundesstadt, or "federal city"” (Wikipedia). Both scenarios are essentially
> a textual entailment problem.
>
>
> In this talk, I will introduce textual entailment problems and solutions
> in different aspects, focusing on the core challenge -- representation
> learning. Particularly, how to learn a dynamic representation for the
> textual description corresponding to specific tasks and contexts? At last,
>  I will discuss some future (ongoing) work for textual entailment, such as
> the commonsense entailment, multimodal entailment etc.
>
> Bio: Wenpeng Yin is a postdoctoral researcher in University of
> Pennsylvania, working with Prof. Dan Roth in textual entailment and
> information extraction. Wenpeng received a Ph.D. degree in 2017 from
> University of Munich, Germany. He had an internship in IBM Watson Research
> Center in early 2016, and got multiple competitive awards in the past,
> including WISE2013 “Best Paper”,  "Baidu Ph.D. Fellowship" in 2014,
> "Chinese Government Award for Outstanding Self-financed Ph.D. Students
> Abroad" in 2016 and “Area Chair Favorites” paper award in COLING2018. He
> serves as the Area Chair for NAACL'2019 and ACL'2019.
>
>
> Host: Kevin Gimpel <kgimpel at ttic.edu>
>
>
>
>
> Mary C. Marre
> Administrative Assistant
> *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 Mon, Mar 11, 2019 at 6:13 PM Mary Marre <mmarre at ttic.edu> wrote:
>
>> When:     Monday, March 18th at *11:00 am*
>>
>> Where:    TTIC, 6045 S Kenwood Avenue, 5th Floor, Room 526
>>
>> *Who:*       Wenpeng Yin, University of Pennsylvania
>>
>>
>> *Title: *Representation Learning in Textual Entailment
>>
>> *Abstract: *Reasoning is a core approach for humans to gain knowledge.
>> Then what knowledge can we obtain from reasoning over a textual
>> description? On the one hand, by a textual description such as “Russia is
>> the largest country in the world, followed by Canada”, we can infer some
>> “new” knowledge such as “Canada is the second largest country in the
>> world”, “Russia is larger than Canada” and “Canada is in top two by size of
>> territorial area” etc. Here, we approach a “new” knowledge world from the
>> textual description. On the other hand, we may infer the truth value of a
>> textual description such as “Zurich is the capital of Switzerland” based on
>> our existing knowledge world. For example, we may doubt and refute that
>> textual description by knowledge “Bern is the de facto capital of
>> Switzerland, referred to by the Swiss as their (e.g. in German)
>> Bundesstadt, or "federal city"” (Wikipedia). Both scenarios are essentially
>> a textual entailment problem.
>>
>>
>> In this talk, I will introduce textual entailment problems and solutions
>> in different aspects, focusing on the core challenge -- representation
>> learning. Particularly, how to learn a dynamic representation for the
>> textual description corresponding to specific tasks and contexts? At last,
>>  I will discuss some future (ongoing) work for textual entailment, such as
>> the commonsense entailment, multimodal entailment etc.
>>
>> Bio: Wenpeng Yin is a postdoctoral researcher in University of
>> Pennsylvania, working with Prof. Dan Roth in textual entailment and
>> information extraction. Wenpeng received a Ph.D. degree in 2017 from
>> University of Munich, Germany. He had an internship in IBM Watson Research
>> Center in early 2016, and got multiple competitive awards in the past,
>> including WISE2013 “Best Paper”,  "Baidu Ph.D. Fellowship" in 2014,
>> "Chinese Government Award for Outstanding Self-financed Ph.D. Students
>> Abroad" in 2016 and “Area Chair Favorites” paper award in COLING2018. He
>> serves as the Area Chair for NAACL'2019 and ACL'2019.
>>
>>
>> Host: Kevin Gimpel <kgimpel at ttic.edu>
>>
>>
>>
>> Mary C. Marre
>> Administrative Assistant
>> *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>*
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20190318/9f6c48c3/attachment-0001.html>