[Theory] NOW: 2/22 Talks at TTIC: Daniel Fried, UC Berkeley

[Mary Marre]

*When:*      Monday, February 22nd at* 11:10 am CT*



*Where:*     Zoom Virtual Talk (*register in advance here
<https://uchicagogroup.zoom.us/webinar/register/WN_ozCMNiORQp-fLZxMDNBCRg>*)



*Who: *       Daniel Fried, UC Berkeley



*Title:  *      Learning Grounded Pragmatic Communication

*Abstract:* To generate language, natural language processing systems
predict what to say---but they should also predict how listeners will
respond. We show how language generation and interpretation across varied
grounded domains can be improved through pragmatic inference: explicitly
reasoning about the actions and intents of the people that the systems
interact with. We train neural speaker and listener models which ground
language into a world context, then layer a pragmatic inference procedure
on top of these models. This pragmatic procedure predicts how human
listeners will interpret text generated by the models, and reasons
counterfactually about why human speakers produced the text they did. We
find this approach improves models' success at generating and interpreting
instructions in real indoor environments, as well as in a challenging
spatial reference dialogue task.

*Bio:* Daniel Fried is a final-year computer science PhD student at UC
Berkeley, advised by Dan Klein. His research in natural language processing
and machine learning focuses on language grounding: tying language to world
contexts, for tasks like visual- and embodied-instruction following, text
generation, and dialogue. Previously, he graduated with a BS from the
University of Arizona and an MPhil from the University of Cambridge. His
work has been supported by a Google PhD Fellowship, an NDSEG Fellowship,
and a Churchill Scholarship.

*Host:* Kevin Gimpel <kgimpel at ttic.edu>
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 Mon, Feb 22, 2021 at 10:23 AM Mary Marre <mmarre at ttic.edu> wrote:

> *When:*      Monday, February 22nd at* 11:10 am CT*
>
>
>
> *Where:*     Zoom Virtual Talk (*register in advance here
> <https://uchicagogroup.zoom.us/webinar/register/WN_ozCMNiORQp-fLZxMDNBCRg>*
> )
>
>
>
> *Who: *       Daniel Fried, UC Berkeley
>
>
>
> *Title:  *      Learning Grounded Pragmatic Communication
>
> *Abstract:* To generate language, natural language processing systems
> predict what to say---but they should also predict how listeners will
> respond. We show how language generation and interpretation across varied
> grounded domains can be improved through pragmatic inference: explicitly
> reasoning about the actions and intents of the people that the systems
> interact with. We train neural speaker and listener models which ground
> language into a world context, then layer a pragmatic inference procedure
> on top of these models. This pragmatic procedure predicts how human
> listeners will interpret text generated by the models, and reasons
> counterfactually about why human speakers produced the text they did. We
> find this approach improves models' success at generating and interpreting
> instructions in real indoor environments, as well as in a challenging
> spatial reference dialogue task.
>
> *Bio:* Daniel Fried is a final-year computer science PhD student at UC
> Berkeley, advised by Dan Klein. His research in natural language processing
> and machine learning focuses on language grounding: tying language to world
> contexts, for tasks like visual- and embodied-instruction following, text
> generation, and dialogue. Previously, he graduated with a BS from the
> University of Arizona and an MPhil from the University of Cambridge. His
> work has been supported by a Google PhD Fellowship, an NDSEG Fellowship,
> and a Churchill Scholarship.
>
> *Host:* Kevin Gimpel <kgimpel at ttic.edu>
>
>
> 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 Sun, Feb 21, 2021 at 4:00 PM Mary Marre <mmarre at ttic.edu> wrote:
>
>> *When:*      Monday, February 22nd at* 11:10 am CT*
>>
>>
>>
>> *Where:*     Zoom Virtual Talk (*register in advance here
>> <https://uchicagogroup.zoom.us/webinar/register/WN_ozCMNiORQp-fLZxMDNBCRg>*
>> )
>>
>>
>>
>> *Who: *       Daniel Fried, UC Berkeley
>>
>>
>>
>> *Title:  *      Learning Grounded Pragmatic Communication
>>
>> *Abstract:* To generate language, natural language processing systems
>> predict what to say---but they should also predict how listeners will
>> respond. We show how language generation and interpretation across varied
>> grounded domains can be improved through pragmatic inference: explicitly
>> reasoning about the actions and intents of the people that the systems
>> interact with. We train neural speaker and listener models which ground
>> language into a world context, then layer a pragmatic inference procedure
>> on top of these models. This pragmatic procedure predicts how human
>> listeners will interpret text generated by the models, and reasons
>> counterfactually about why human speakers produced the text they did. We
>> find this approach improves models' success at generating and interpreting
>> instructions in real indoor environments, as well as in a challenging
>> spatial reference dialogue task.
>>
>> *Bio:* Daniel Fried is a final-year computer science PhD student at UC
>> Berkeley, advised by Dan Klein. His research in natural language processing
>> and machine learning focuses on language grounding: tying language to world
>> contexts, for tasks like visual- and embodied-instruction following, text
>> generation, and dialogue. Previously, he graduated with a BS from the
>> University of Arizona and an MPhil from the University of Cambridge. His
>> work has been supported by a Google PhD Fellowship, an NDSEG Fellowship,
>> and a Churchill Scholarship.
>>
>> *Host:* Kevin Gimpel <kgimpel at ttic.edu>
>>
>>
>>
>>
>> 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 Mon, Feb 15, 2021 at 9:29 PM Mary Marre <mmarre at ttic.edu> wrote:
>>
>>> *When:*      Monday, February 22nd at* 11:10 am CT*
>>>
>>>
>>>
>>> *Where:*     Zoom Virtual Talk (*register in advance here
>>> <https://uchicagogroup.zoom.us/webinar/register/WN_ozCMNiORQp-fLZxMDNBCRg>*
>>> )
>>>
>>>
>>>
>>> *Who: *       Daniel Fried, UC Berkeley
>>>
>>>
>>>
>>> *Title:  *      Learning Grounded Pragmatic Communication
>>>
>>> *Abstract:* To generate language, natural language processing systems
>>> predict what to say---but they should also predict how listeners will
>>> respond. We show how language generation and interpretation across varied
>>> grounded domains can be improved through pragmatic inference: explicitly
>>> reasoning about the actions and intents of the people that the systems
>>> interact with. We train neural speaker and listener models which ground
>>> language into a world context, then layer a pragmatic inference procedure
>>> on top of these models. This pragmatic procedure predicts how human
>>> listeners will interpret text generated by the models, and reasons
>>> counterfactually about why human speakers produced the text they did. We
>>> find this approach improves models' success at generating and interpreting
>>> instructions in real indoor environments, as well as in a challenging
>>> spatial reference dialogue task.
>>>
>>> *Bio:* Daniel Fried is a final-year computer science PhD student at UC
>>> Berkeley, advised by Dan Klein. His research in natural language processing
>>> and machine learning focuses on language grounding: tying language to world
>>> contexts, for tasks like visual- and embodied-instruction following, text
>>> generation, and dialogue. Previously, he graduated with a BS from the
>>> University of Arizona and an MPhil from the University of Cambridge. His
>>> work has been supported by a Google PhD Fellowship, an NDSEG Fellowship,
>>> and a Churchill Scholarship.
>>>
>>> *Host:* Kevin Gimpel <kgimpel at ttic.edu>
>>>
>>>
>>>
>>>
>>>
>>> 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>*
>>>
>>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20210222/6d2cc8a0/attachment-0001.html>