[Colloquium] NOW: 11/17 NLP Seminar: Jacob Andreas, MIT
Mary Marre
mmarre at ttic.edu
Thu Nov 17 12:31:03 CST 2022
*PLEASE NOTE SPECIAL TIME!*
*When:* Thursday, November 17th at* 12:30** p**m CT *
*Where: *Talk will be given *live, in-person* at
TTIC, 6045 S. Kenwood Avenue
5th Floor, Room 530
*Virtually:* *via* Panopto (*livestream
<https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=8660ee27-1edf-4423-8442-af49000135f5>*
)
*Who: * Jacob Andreas, MIT
------------------------------
*Title:* Toward Natural Language Supervision
*Abstract: *In the age of deep networks, "learning" almost invariably means
"learning from examples". Image classifiers are trained with large datasets
of images, machine translation systems with corpora of translated
sentences, and robot policies with rollouts or demonstrations. When human
learners acquire new concepts and skills, we often do so with richer
supervision, especially in the form of language---we learn new concepts
from exemplars accompanied by descriptions or definitions, and new skills
from demonstrations accompanied by instructions. In natural language
processing, recent years have seen a number of successful approaches to
learning from task definitions and other forms of auxiliary language-based
supervision. But these successes have been largely confined to tasks that
also involve language as an input and an output---what will it take to make
language-based training useful for the rest of the machine learning
ecosystem? In this talk, I'll present two recent applications of natural
language supervision to tasks outside the traditional domain of NLP: using
language to guide visuomotor policy learning and inductive program
synthesis. In these applications, natural language annotations reveal
latent compositional structure in the space of programs and plans, helping
models discover reusable abstractions for perception and interaction. This
kind of compositional structure is present in many tasks beyond policy
learning and program synthesis, and I'll conclude with a brief discussion
of how these techniques can be applied even more generally.
*Bio: *Jacob Andreas is the X Consortium Assistant Professor at MIT. His
research aims to build intelligent systems that can communicate effectively
using language and learn from human guidance. Jacob earned his Ph.D. from
UC Berkeley, his M.Phil. from Cambridge (where he studied as a Churchill
scholar) and his B.S. from Columbia. As a researcher at Microsoft Semantic
Machines, he founded the language generation team and helped develop core
pieces of the technology that powers conversational interaction in
Microsoft Outlook. He has been named a Samsung AI Researcher of the Year
and National Academy of Sciences Kavli Fellow, and has received MIT's
Kolokotrones teaching award and paper awards at NAACL and ICML.
*Host: Chenhao Tan <chenhao at uchicago.edu>*
**************************************************************************************************
The *NLP** Seminar* is a joint weekly meetup of researchers interested in
*Natural Language Processing* across TTIC and UChicago that often hosts
external NLP researchers to talk about their research. The seminar is
typically held on Thursdays at noon.
Mary C. Marre
Faculty Administrative Support
*Toyota Technological Institute*
*6045 S. Kenwood Avenue, Rm 517*
*Chicago, IL 60637*
*773-834-1757*
*mmarre at ttic.edu <mmarre at ttic.edu>*
On Thu, Nov 17, 2022 at 10:53 AM Mary Marre <mmarre at ttic.edu> wrote:
> *PLEASE NOTE SPECIAL TIME!*
>
> *When:* Thursday, November 17th at* 12:30** p**m CT *
>
>
> *Where: *Talk will be given *live, in-person* at
>
> TTIC, 6045 S. Kenwood Avenue
>
> 5th Floor, Room 530
>
>
> *Virtually:* *via* Panopto (*livestream
> <https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=8660ee27-1edf-4423-8442-af49000135f5>*
> )
>
>
> *Who: * Jacob Andreas, MIT
>
>
> ------------------------------
>
> *Title:* Toward Natural Language Supervision
> *Abstract: *In the age of deep networks, "learning" almost invariably
> means "learning from examples". Image classifiers are trained with large
> datasets of images, machine translation systems with corpora of translated
> sentences, and robot policies with rollouts or demonstrations. When human
> learners acquire new concepts and skills, we often do so with richer
> supervision, especially in the form of language---we learn new concepts
> from exemplars accompanied by descriptions or definitions, and new skills
> from demonstrations accompanied by instructions. In natural language
> processing, recent years have seen a number of successful approaches to
> learning from task definitions and other forms of auxiliary language-based
> supervision. But these successes have been largely confined to tasks that
> also involve language as an input and an output---what will it take to make
> language-based training useful for the rest of the machine learning
> ecosystem? In this talk, I'll present two recent applications of natural
> language supervision to tasks outside the traditional domain of NLP: using
> language to guide visuomotor policy learning and inductive program
> synthesis. In these applications, natural language annotations reveal
> latent compositional structure in the space of programs and plans, helping
> models discover reusable abstractions for perception and interaction. This
> kind of compositional structure is present in many tasks beyond policy
> learning and program synthesis, and I'll conclude with a brief discussion
> of how these techniques can be applied even more generally.
>
> *Bio: *Jacob Andreas is the X Consortium Assistant Professor at MIT. His
> research aims to build intelligent systems that can communicate effectively
> using language and learn from human guidance. Jacob earned his Ph.D. from
> UC Berkeley, his M.Phil. from Cambridge (where he studied as a Churchill
> scholar) and his B.S. from Columbia. As a researcher at Microsoft Semantic
> Machines, he founded the language generation team and helped develop core
> pieces of the technology that powers conversational interaction in
> Microsoft Outlook. He has been named a Samsung AI Researcher of the Year
> and National Academy of Sciences Kavli Fellow, and has received MIT's
> Kolokotrones teaching award and paper awards at NAACL and ICML.
>
> *Host: Chenhao Tan <chenhao at uchicago.edu>*
>
>
> **************************************************************************************************
>
> The *NLP** Seminar* is a joint weekly meetup of researchers interested in
> *Natural Language Processing* across TTIC and UChicago that often hosts
> external NLP researchers to talk about their research. The seminar is
> typically held on Thursdays at noon.
>
>
>
>
> Mary C. Marre
> Faculty Administrative Support
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue, Rm 517*
> *Chicago, IL 60637*
> *773-834-1757*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
>
> On Wed, Nov 16, 2022 at 6:33 PM Mary Marre <mmarre at ttic.edu> wrote:
>
>> *PLEASE NOTE SPECIAL TIME!*
>>
>> *When:* Thursday, November 17th at* 12:30** p**m CT *
>>
>>
>> *Where: *Talk will be given *live, in-person* at
>>
>> TTIC, 6045 S. Kenwood Avenue
>>
>> 5th Floor, Room 530
>>
>>
>> *Virtually:* *via* Panopto (*livestream
>> <https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=8660ee27-1edf-4423-8442-af49000135f5>*
>> )
>>
>>
>> *Who: * Jacob Andreas, MIT
>>
>>
>> ------------------------------
>>
>> *Title:* Toward Natural Language Supervision
>> *Abstract: *In the age of deep networks, "learning" almost invariably
>> means "learning from examples". Image classifiers are trained with large
>> datasets of images, machine translation systems with corpora of translated
>> sentences, and robot policies with rollouts or demonstrations. When human
>> learners acquire new concepts and skills, we often do so with richer
>> supervision, especially in the form of language---we learn new concepts
>> from exemplars accompanied by descriptions or definitions, and new skills
>> from demonstrations accompanied by instructions. In natural language
>> processing, recent years have seen a number of successful approaches to
>> learning from task definitions and other forms of auxiliary language-based
>> supervision. But these successes have been largely confined to tasks that
>> also involve language as an input and an output---what will it take to
>> make language-based training useful for the rest of the machine learning
>> ecosystem? In this talk, I'll present two recent applications of natural
>> language supervision to tasks outside the traditional domain of NLP:
>> using language to guide visuomotor policy learning and inductive program
>> synthesis. In these applications, natural language annotations reveal
>> latent compositional structure in the space of programs and plans, helping
>> models discover reusable abstractions for perception and interaction. This
>> kind of compositional structure is present in many tasks beyond policy
>> learning and program synthesis, and I'll conclude with a brief discussion
>> of how these techniques can be applied even more generally.
>>
>> *Bio: *Jacob Andreas is the X Consortium Assistant Professor at MIT. His
>> research aims to build intelligent systems that can communicate effectively
>> using language and learn from human guidance. Jacob earned his Ph.D.
>> from UC Berkeley, his M.Phil. from Cambridge (where he studied as a
>> Churchill scholar) and his B.S. from Columbia. As a researcher at Microsoft
>> Semantic Machines, he founded the language generation team and helped
>> develop core pieces of the technology that powers conversational
>> interaction in Microsoft Outlook. He has been named a Samsung AI Researcher
>> of the Year and National Academy of Sciences Kavli Fellow, and has received
>> MIT's Kolokotrones teaching award and paper awards at NAACL and ICML.
>>
>> *Host: Chenhao Tan <chenhao at uchicago.edu>*
>>
>>
>> **************************************************************************************************
>>
>> The *NLP** Seminar* is a joint weekly meetup of researchers interested
>> in *Natural Language Processing* across TTIC and UChicago that often
>> hosts external NLP researchers to talk about their research. The seminar is
>> typically held on Thursdays at noon.
>>
>>
>>
>>
>>
>>
>> Mary C. Marre
>> Faculty Administrative Support
>> *Toyota Technological Institute*
>> *6045 S. Kenwood Avenue, Rm 517*
>> *Chicago, IL 60637*
>> *773-834-1757*
>> *mmarre at ttic.edu <mmarre at ttic.edu>*
>>
>>
>> On Thu, Nov 10, 2022 at 6:23 PM Mary Marre <mmarre at ttic.edu> wrote:
>>
>>> *PLEASE NOTE SPECIAL TIME!*
>>>
>>> *When:* Thursday, November 17th at* 12:30** p**m CT *
>>>
>>>
>>> *Where: *Talk will be given *live, in-person* at
>>>
>>> TTIC, 6045 S. Kenwood Avenue
>>>
>>> 5th Floor, Room 530
>>>
>>>
>>> *Virtually:* *via* Panopto (*livestream
>>> <https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=8660ee27-1edf-4423-8442-af49000135f5>*
>>> )
>>>
>>>
>>> *Who: * Jacob Andreas, MIT
>>>
>>>
>>> ------------------------------
>>>
>>> *Title:* Toward Natural Language Supervision
>>> *Abstract: *In the age of deep networks, "learning" almost invariably
>>> means "learning from examples". Image classifiers are trained with large
>>> datasets of images, machine translation systems with corpora of translated
>>> sentences, and robot policies with rollouts or demonstrations. When human
>>> learners acquire new concepts and skills, we often do so with richer
>>> supervision, especially in the form of language---we learn new concepts
>>> from exemplars accompanied by descriptions or definitions, and new skills
>>> from demonstrations accompanied by instructions. In natural language
>>> processing, recent years have seen a number of successful approaches to
>>> learning from task definitions and other forms of auxiliary language-based
>>> supervision. But these successes have been largely confined to tasks that
>>> also involve language as an input and an output---what will it take to make
>>> language-based training useful for the rest of the machine learning
>>> ecosystem? In this talk, I'll present two recent applications of natural
>>> language supervision to tasks outside the traditional domain of NLP: using
>>> language to guide visuomotor policy learning and inductive program
>>> synthesis. In these applications, natural language annotations reveal
>>> latent compositional structure in the space of programs and plans, helping
>>> models discover reusable abstractions for perception and interaction. This
>>> kind of compositional structure is present in many tasks beyond policy
>>> learning and program synthesis, and I'll conclude with a brief discussion
>>> of how these techniques can be applied even more generally.
>>>
>>> *Bio: *Jacob Andreas is the X Consortium Assistant Professor at MIT.
>>> His research aims to build intelligent systems that can communicate
>>> effectively using language and learn from human guidance. Jacob earned his
>>> Ph.D. from UC Berkeley, his M.Phil. from Cambridge (where he studied as a
>>> Churchill scholar) and his B.S. from Columbia. As a researcher at Microsoft
>>> Semantic Machines, he founded the language generation team and helped
>>> develop core pieces of the technology that powers conversational
>>> interaction in Microsoft Outlook. He has been named a Samsung AI Researcher
>>> of the Year and National Academy of Sciences Kavli Fellow, and has received
>>> MIT's Kolokotrones teaching award and paper awards at NAACL and ICML.
>>>
>>> *Host: Chenhao Tan <chenhao at uchicago.edu>*
>>>
>>>
>>> **************************************************************************************************
>>>
>>> The *NLP** Seminar* is a joint weekly meetup of researchers interested
>>> in *Natural Language Processing* across TTIC and UChicago that often
>>> hosts external NLP researchers to talk about their research. The seminar is
>>> typically held on Thursdays at noon.
>>>
>>>
>>>
>>>
>>> Mary C. Marre
>>> Faculty Administrative Support
>>> *Toyota Technological Institute*
>>> *6045 S. Kenwood Avenue, Rm 517*
>>> *Chicago, IL 60637*
>>> *773-834-1757*
>>> *mmarre at ttic.edu <mmarre at ttic.edu>*
>>>
>>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20221117/104d51de/attachment-0001.html>
More information about the Colloquium
mailing list