[Theory] NOW: 1/11 Young Researcher Seminar Series: Elena Voita, FAIR
Mary Marre
mmarre at ttic.edu
Wed Jan 11 10:30:46 CST 2023
*When:* Wednesday, January 11th at* 10:30** a**m CT *
*Virtually:* *via* Zoom (*livestream
<https://uchicagogroup.zoom.us/webinar/register/WN_nPU7Whf8ScGE2AcsLnhhKg>*)
*Who: * Elena Voita, FAIR
------------------------------
*Title: * A Journey on Interpretability Methods in NLP: Inside-Out
and Back
*Abstract: *In this talk, I will illustrate several approaches, motivations
and ideas behind analysis of NLP models. As an example, we will take the
standard Transformer model trained for the Machine Translation task and
will look at it from different points of view. We will start our journey
from examining model components and seeing how, and whether, model’s
inductive biases facilitate performing the task. Next, we turn to the kinds
of information the model relies on to make its predictions. Here we will
use attribution methods and will see how some potentially pathological
behaviours look on the inside. Finally, we will turn our view inside-out,
i.e. from inner workings of the model to analysing its outputs. In this
part, we will discover that the way the model learns to translate is very
similar to how humans do it: from learning word-by-word translation first
to becoming more fluent later. Most importantly, the two views (from the
inside and from the outside) show the same process, and we will see how
this process is reflected in these two types of analysis.
*Bio: *Elena (Lena) Voita is a Research Scientist at Facebook AI Research
(joined recently). She is mostly interested in understanding what and how
neural models learn. Previously, she was a PhD student at the University of
Edinburgh supervised by Ivan Titov and Rico Sennrich, was awarded Facebook
PhD Fellowship, worked as a Research Scientist at Yandex Research side by
side with the Yandex Translate team. She enjoys writing blog posts and
teaching; a public version of (a part of) her NLP course is available at NLP
Course For You <https://lena-voita.github.io/nlp_course.html>.
*Host: Karen Livescu <klivescu at ttic.edu>*
**************************************************************************************************
The *TTIC Young Researcher Seminar Series* (
http://www.ttic.edu/young-researcher.php) features talks by Ph.D. students
and postdocs whose research is of broad interest to the computer science
community. The series provides an opportunity for early-career researchers to
present recent work to and meet with students and faculty at TTIC and
nearby universities.
The seminars are typically held on Wednesdays at 10:30am in TTIC Room 530.
For additional information, please contact *David McAllester *(
mcallester at ttic.edu).
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, Jan 11, 2023 at 9:13 AM Mary Marre <mmarre at ttic.edu> wrote:
> *When:* Wednesday, January 11th at* 10:30** a**m CT *
>
>
> *Virtually:* *via* Zoom (*livestream
> <https://uchicagogroup.zoom.us/webinar/register/WN_nPU7Whf8ScGE2AcsLnhhKg>*
> )
>
>
> *Who: * Elena Voita, FAIR
>
>
> ------------------------------
>
> *Title: * A Journey on Interpretability Methods in NLP: Inside-Out
> and Back
> *Abstract: *In this talk, I will illustrate several approaches,
> motivations and ideas behind analysis of NLP models. As an example, we will
> take the standard Transformer model trained for the Machine Translation
> task and will look at it from different points of view. We will start our
> journey from examining model components and seeing how, and whether,
> model’s inductive biases facilitate performing the task. Next, we turn to
> the kinds of information the model relies on to make its predictions. Here
> we will use attribution methods and will see how some potentially
> pathological behaviours look on the inside. Finally, we will turn our view
> inside-out, i.e. from inner workings of the model to analysing its outputs.
> In this part, we will discover that the way the model learns to translate
> is very similar to how humans do it: from learning word-by-word translation
> first to becoming more fluent later. Most importantly, the two views
> (from the inside and from the outside) show the same process, and we will
> see how this process is reflected in these two types of analysis.
>
> *Bio: *Elena (Lena) Voita is a Research Scientist at Facebook AI Research
> (joined recently). She is mostly interested in understanding what and how
> neural models learn. Previously, she was a PhD student at the University of
> Edinburgh supervised by Ivan Titov and Rico Sennrich, was awarded Facebook
> PhD Fellowship, worked as a Research Scientist at Yandex Research side by
> side with the Yandex Translate team. She enjoys writing blog posts and
> teaching; a public version of (a part of) her NLP course is available at NLP
> Course For You <https://lena-voita.github.io/nlp_course.html>.
>
> *Host: Karen Livescu <klivescu at ttic.edu>*
>
>
> **************************************************************************************************
>
> The *TTIC Young Researcher Seminar Series* (
> http://www.ttic.edu/young-researcher.php) features talks by Ph.D.
> students and postdocs whose research is of broad interest to the computer
> science community. The series provides an opportunity for early-career
> researchers to present recent work to and meet with students and faculty
> at TTIC and nearby universities.
>
>
> The seminars are typically held on Wednesdays at 10:30am in TTIC Room 530.
>
> For additional information, please contact *David McAllester *(
> mcallester at ttic.edu).
>
>
>
>
>
> 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 Tue, Jan 10, 2023 at 3:22 PM Mary Marre <mmarre at ttic.edu> wrote:
>
>> *When:* Wednesday, January 11th at* 10:30** a**m CT *
>>
>>
>> *Virtually:* *via* Zoom (*livestream
>> <https://uchicagogroup.zoom.us/webinar/register/WN_nPU7Whf8ScGE2AcsLnhhKg>*
>> )
>>
>>
>> *Who: * Elena Voita, FAIR
>>
>>
>> ------------------------------
>>
>> *Title: * A Journey on Interpretability Methods in NLP: Inside-Out
>> and Back
>> *Abstract: *In this talk, I will illustrate several approaches,
>> motivations and ideas behind analysis of NLP models. As an example, we will
>> take the standard Transformer model trained for the Machine Translation
>> task and will look at it from different points of view. We will start our
>> journey from examining model components and seeing how, and whether,
>> model’s inductive biases facilitate performing the task. Next, we turn to
>> the kinds of information the model relies on to make its predictions. Here
>> we will use attribution methods and will see how some potentially
>> pathological behaviours look on the inside. Finally, we will turn our view
>> inside-out, i.e. from inner workings of the model to analysing its outputs.
>> In this part, we will discover that the way the model learns to translate
>> is very similar to how humans do it: from learning word-by-word translation
>> first to becoming more fluent later. Most importantly, the two views
>> (from the inside and from the outside) show the same process, and we will
>> see how this process is reflected in these two types of analysis.
>>
>> *Bio: *Elena (Lena) Voita is a Research Scientist at Facebook AI
>> Research (joined recently). She is mostly interested in understanding what
>> and how neural models learn. Previously, she was a PhD student at the
>> University of Edinburgh supervised by Ivan Titov and Rico Sennrich, was
>> awarded Facebook PhD Fellowship, worked as a Research Scientist at Yandex
>> Research side by side with the Yandex Translate team. She enjoys writing
>> blog posts and teaching; a public version of (a part of) her NLP course is
>> available at NLP Course For You
>> <https://lena-voita.github.io/nlp_course.html>.
>>
>> *Host: Karen Livescu <klivescu at ttic.edu>*
>>
>>
>> **************************************************************************************************
>>
>> The *TTIC Young Researcher Seminar Series* (
>> http://www.ttic.edu/young-researcher.php) features talks by Ph.D.
>> students and postdocs whose research is of broad interest to the
>> computer science community. The series provides an opportunity
>> for early-career researchers to present recent work to and meet with
>> students and faculty at TTIC and nearby universities.
>>
>>
>> The seminars are typically held on Wednesdays at 10:30am in TTIC Room 530.
>>
>> For additional information, please contact *David McAllester *(
>> mcallester at ttic.edu).
>>
>>
>>
>>
>> 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 Fri, Jan 6, 2023 at 10:58 AM Mary Marre <mmarre at ttic.edu> wrote:
>>
>>> *When:* Wednesday, January 11th at* 10:30** a**m CT *
>>>
>>>
>>> *Virtually:* *via* Zoom (*livestream
>>> <https://uchicagogroup.zoom.us/webinar/register/WN_nPU7Whf8ScGE2AcsLnhhKg>*
>>> )
>>>
>>>
>>> *Who: * Elena Voita, FAIR
>>>
>>>
>>> ------------------------------
>>>
>>> *Title: * A Journey on Interpretability Methods in NLP:
>>> Inside-Out and Back
>>> *Abstract: *In this talk, I will illustrate several approaches,
>>> motivations and ideas behind analysis of NLP models. As an example, we will
>>> take the standard Transformer model trained for the Machine Translation
>>> task and will look at it from different points of view. We will start our
>>> journey from examining model components and seeing how, and whether,
>>> model’s inductive biases facilitate performing the task. Next, we turn to
>>> the kinds of information the model relies on to make its predictions. Here
>>> we will use attribution methods and will see how some potentially
>>> pathological behaviours look on the inside. Finally, we will turn our view
>>> inside-out, i.e. from inner workings of the model to analysing its outputs.
>>> In this part, we will discover that the way the model learns to translate
>>> is very similar to how humans do it: from learning word-by-word translation
>>> first to becoming more fluent later. Most importantly, the two views
>>> (from the inside and from the outside) show the same process, and we will
>>> see how this process is reflected in these two types of analysis.
>>>
>>> *Bio: *Elena (Lena) Voita is a Research Scientist at Facebook AI
>>> Research (joined recently). She is mostly interested in understanding what
>>> and how neural models learn. Previously, she was a PhD student at the
>>> University of Edinburgh supervised by Ivan Titov and Rico Sennrich, was
>>> awarded Facebook PhD Fellowship, worked as a Research Scientist at Yandex
>>> Research side by side with the Yandex Translate team. She enjoys writing
>>> blog posts and teaching; a public version of (a part of) her NLP course is
>>> available at NLP Course For You
>>> <https://lena-voita.github.io/nlp_course.html>.
>>>
>>> *Host: Karen Livescu <klivescu at ttic.edu>*
>>>
>>>
>>> **************************************************************************************************
>>>
>>> The *TTIC Young Researcher Seminar Series* (http://www.ttic.edu/young-
>>> researcher.php) features talks by Ph.D. students and postdocs whose
>>> research is of broad interest to the computer science community.
>>> The series provides an opportunity for early-career researchers to
>>> present recent work to and meet with students and faculty at TTIC and
>>> nearby universities.
>>>
>>>
>>> The seminars are typically held on Wednesdays at 10:30am in TTIC Room
>>> 530.
>>>
>>> For additional information, please contact *David McAllester *(
>>> mcallester at ttic.edu).
>>>
>>>
>>>
>>> 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/theory/attachments/20230111/68d30b81/attachment-0001.html>
More information about the Theory
mailing list