[Theory] NOW: 6/7 TTIC Colloquium: Chenhao Tan, University of Chicago

Mary Marre mmarre at ttic.edu
Mon Jun 7 11:07:40 CDT 2021


*When:*      Monday, June 7th, 2021 at *11:10 am CT*



*Where:*     Zoom Virtual Talk (*register in advance here
<https://uchicagogroup.zoom.us/webinar/register/WN_IHra3-9YTAWZOsxP9t5ZRA>*)



*Who: *       Chenhao Tan, University of Chicago


*Title:*       Characterizing the "Value" of Information

*Abstract:* Data are central to recent advances in artificial intelligence.
However, not all data contain valuable information. In this work, I will
present several projects in understanding the value of information. First,
I will quantify the value of textual information in medical notes with a
probing framework and show that selected valuable information can
outperform using the entirety of notes. Second, I will examine the value of
explanations in the form of rationales, a subset of input tokens, and
discuss insights that can be used to improve learning from rationales.
Finally, I will give an overview of my research to help identify
overlapping interests and collaboration opportunities with the TTIC
community.

*Bio:* Chenhao Tan is an assistant professor of computer science at the
University of Chicago, and is also affiliated with the Harris School of
Public Policy. He obtained his PhD degree in the Department of Computer
Science at Cornell University and bachelor's degrees in computer science
and in economics from Tsinghua University. Prior to joining the University
of Chicago, he was an assistant professor at the University of Colorado
Boulder and a postdoc at the University of Washington. His research
interests include natural language processing, human-centered AI, and
computational social science. His work has been covered by many news media
outlets, such as the New York Times and the Washington Post. He also won an
NSF CAREER award, an NSF CRII award, a Salesforce research award, an Amazon
research award, a Facebook fellowship, and a Yahoo! Key Scientific
Challenges award.

*Host:  **Karen Livescu* <klivescu at ttic.edu>
For more information on the colloquium series or to subscribe to the
mailing list, please see http://www.ttic.edu/colloquium.php

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, Jun 7, 2021 at 10:00 AM Mary Marre <mmarre at ttic.edu> wrote:

> *When:*      Monday, June 7th, 2021 at *11:10 am CT*
>
>
>
> *Where:*     Zoom Virtual Talk (*register in advance here
> <https://uchicagogroup.zoom.us/webinar/register/WN_IHra3-9YTAWZOsxP9t5ZRA>*
> )
>
>
>
> *Who: *       Chenhao Tan, University of Chicago
>
>
> *Title:*       Characterizing the "Value" of Information
>
> *Abstract:* Data are central to recent advances in artificial
> intelligence. However, not all data contain valuable information. In this
> work, I will present several projects in understanding the value of
> information. First, I will quantify the value of textual information in
> medical notes with a probing framework and show that selected valuable
> information can outperform using the entirety of notes. Second, I will
> examine the value of explanations in the form of rationales, a subset of
> input tokens, and discuss insights that can be used to improve learning
> from rationales. Finally, I will give an overview of my research to help
> identify overlapping interests and collaboration opportunities with the
> TTIC community.
>
> *Bio:* Chenhao Tan is an assistant professor of computer science at the
> University of Chicago, and is also affiliated with the Harris School of
> Public Policy. He obtained his PhD degree in the Department of Computer
> Science at Cornell University and bachelor's degrees in computer science
> and in economics from Tsinghua University. Prior to joining the University
> of Chicago, he was an assistant professor at the University of Colorado
> Boulder and a postdoc at the University of Washington. His research
> interests include natural language processing, human-centered AI, and
> computational social science. His work has been covered by many news media
> outlets, such as the New York Times and the Washington Post. He also won an
> NSF CAREER award, an NSF CRII award, a Salesforce research award, an Amazon
> research award, a Facebook fellowship, and a Yahoo! Key Scientific
> Challenges award.
>
> *Host:  **Karen Livescu* <klivescu at ttic.edu>
> For more information on the colloquium series or to subscribe to the
> mailing list, please see http://www.ttic.edu/colloquium.php
>
>
>
>
>
> 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, Jun 6, 2021 at 4:58 PM Mary Marre <mmarre at ttic.edu> wrote:
>
>> *When:*      Monday, June 7th, 2021 at *11:10 am CT*
>>
>>
>>
>> *Where:*     Zoom Virtual Talk (*register in advance here
>> <https://uchicagogroup.zoom.us/webinar/register/WN_IHra3-9YTAWZOsxP9t5ZRA>*
>> )
>>
>>
>>
>> *Who: *       Chenhao Tan, University of Chicago
>>
>>
>> *Title:*       Characterizing the "Value" of Information
>>
>> *Abstract:* Data are central to recent advances in artificial
>> intelligence. However, not all data contain valuable information. In this
>> work, I will present several projects in understanding the value of
>> information. First, I will quantify the value of textual information in
>> medical notes with a probing framework and show that selected valuable
>> information can outperform using the entirety of notes. Second, I will
>> examine the value of explanations in the form of rationales, a subset of
>> input tokens, and discuss insights that can be used to improve learning
>> from rationales. Finally, I will give an overview of my research to help
>> identify overlapping interests and collaboration opportunities with the
>> TTIC community.
>>
>> *Bio:* Chenhao Tan is an assistant professor of computer science at the
>> University of Chicago, and is also affiliated with the Harris School of
>> Public Policy. He obtained his PhD degree in the Department of Computer
>> Science at Cornell University and bachelor's degrees in computer science
>> and in economics from Tsinghua University. Prior to joining the University
>> of Chicago, he was an assistant professor at the University of Colorado
>> Boulder and a postdoc at the University of Washington. His research
>> interests include natural language processing, human-centered AI, and
>> computational social science. His work has been covered by many news media
>> outlets, such as the New York Times and the Washington Post. He also won an
>> NSF CAREER award, an NSF CRII award, a Salesforce research award, an Amazon
>> research award, a Facebook fellowship, and a Yahoo! Key Scientific
>> Challenges award.
>>
>> *Host:  **Karen Livescu* <klivescu at ttic.edu>
>> For more information on the colloquium series or to subscribe to the
>> mailing list, please see http://www.ttic.edu/colloquium.php
>>
>>
>>
>>
>>
>>
>> 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 Mon, May 31, 2021 at 3:13 PM Mary Marre <mmarre at ttic.edu> wrote:
>>
>>> *When:*      Monday, June 7th, 2021 at *11:10 am CT*
>>>
>>>
>>>
>>> *Where:*     Zoom Virtual Talk (*register in advance here
>>> <https://uchicagogroup.zoom.us/webinar/register/WN_IHra3-9YTAWZOsxP9t5ZRA>*
>>> )
>>>
>>>
>>>
>>> *Who: *       Chenhao Tan, University of Chicago
>>>
>>>
>>> *Title:*       Characterizing the "Value" of Information
>>>
>>> *Abstract:* Data are central to recent advances in artificial
>>> intelligence. However, not all data contain valuable information. In this
>>> work, I will present several projects in understanding the value of
>>> information. First, I will quantify the value of textual information in
>>> medical notes with a probing framework and show that selected valuable
>>> information can outperform using the entirety of notes. Second, I will
>>> examine the value of explanations in the form of rationales, a subset of
>>> input tokens, and discuss insights that can be used to improve learning
>>> from rationales. Finally, I will give an overview of my research to help
>>> identify overlapping interests and collaboration opportunities with the
>>> TTIC community.
>>>
>>> *Bio:* Chenhao Tan is an assistant professor of computer science at the
>>> University of Chicago, and is also affiliated with the Harris School of
>>> Public Policy. He obtained his PhD degree in the Department of Computer
>>> Science at Cornell University and bachelor's degrees in computer science
>>> and in economics from Tsinghua University. Prior to joining the University
>>> of Chicago, he was an assistant professor at the University of Colorado
>>> Boulder and a postdoc at the University of Washington. His research
>>> interests include natural language processing, human-centered AI, and
>>> computational social science. His work has been covered by many news media
>>> outlets, such as the New York Times and the Washington Post. He also won an
>>> NSF CAREER award, an NSF CRII award, a Salesforce research award, an Amazon
>>> research award, a Facebook fellowship, and a Yahoo! Key Scientific
>>> Challenges award.
>>>
>>> *Host:  **Karen Livescu* <klivescu at ttic.edu>
>>> For more information on the colloquium series or to subscribe to the
>>> mailing list, please see http://www.ttic.edu/colloquium.php
>>>
>>>
>>>
>>>
>>>
>>> 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/20210607/5f3e6584/attachment-0001.html>


More information about the Theory mailing list