[Colloquium] NOW: 3/20 Talks at TTIC: Lianhui Qin, University of Washington
Mary Marre
mmarre at ttic.edu
Mon Mar 20 11:33:51 CDT 2023
*When:* Monday, March 20, 2023 at* 11:30** a**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=4ae2d7b2-686d-4e3e-aa42-afc40169d0af>*
)
*Who: * Lianhui Qin, University of Washington
------------------------------
*Title: *Constrained, Casual, and Logical Reasoning for Neural
Language Generation
*Abstract:* Today’s language models (LMs) can produce human-like fluent
text. However, they generate words with no grounding in the world and
cannot flexibly reason about everyday situations and events, such as
counterfactual (“what if?”) and abductive (“what might explain these
observations?”) reasoning that are important forms of human cognition
activities. In this talk, I will present my research on connecting
reasoning with language generation. Reasoning for language generation poses
several key challenges, including incorporating diverse contextual
constraints on the fly, understanding cause and effect when events unfold,
and grounding on logic structures for consistent reasoning. I will first
discuss COLD decoding, a unified energy-based framework for any
off-the-shelf LMs to reason with arbitrary constraints. It also introduces
differentiable reasoning over discrete symbolic text for improved
efficiency. Secondly, I will focus on a particularly important form of
reasoning, counterfactual reasoning, including its first formulation in
language generation and our algorithm, DeLorean, that enables off-the-shelf
LMs to capture causal invariance. Thirdly, I will present Maieutic
prompting, which improves the logical consistency of neural reasoning by
integrating with logic structures. I will conclude with future research
toward more general, grounded, and trustworthy reasoning with language.
*Bio: *Lianhui Qin is a final year PhD student in Paul G. Allen School of
Computer Science & Engineering at University of Washington, advised by
Prof. Yejin Choi. Her research interests lie in natural language
processing, artificial intelligence, and machine learning, with a
particular focus on natural language reasoning and generation. Her research
has been recognized with Best Paper Award at NAACL 2022, Best Paper Award
at WeCNLP 2020, Best Demo Paper Nomination at ACL 2019, as well as
Microsoft Research PhD Fellowship.
*Host: *Matthew Walter <mwalter at ttic.edu>
<klivescu 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 Mon, Mar 20, 2023 at 10:30 AM Mary Marre <mmarre at ttic.edu> wrote:
> *When:* Monday, March 20, 2023 at* 11:30** a**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=4ae2d7b2-686d-4e3e-aa42-afc40169d0af>*
> )
>
>
> *Who: * Lianhui Qin, University of Washington
>
>
> ------------------------------
> *Title: *Constrained, Casual, and Logical Reasoning for Neural
> Language Generation
>
> *Abstract:* Today’s language models (LMs) can produce human-like fluent
> text. However, they generate words with no grounding in the world and
> cannot flexibly reason about everyday situations and events, such as
> counterfactual (“what if?”) and abductive (“what might explain these
> observations?”) reasoning that are important forms of human cognition
> activities. In this talk, I will present my research on connecting
> reasoning with language generation. Reasoning for language generation poses
> several key challenges, including incorporating diverse contextual
> constraints on the fly, understanding cause and effect when events unfold,
> and grounding on logic structures for consistent reasoning. I will first
> discuss COLD decoding, a unified energy-based framework for any
> off-the-shelf LMs to reason with arbitrary constraints. It also introduces
> differentiable reasoning over discrete symbolic text for improved
> efficiency. Secondly, I will focus on a particularly important form of
> reasoning, counterfactual reasoning, including its first formulation in
> language generation and our algorithm, DeLorean, that enables off-the-shelf
> LMs to capture causal invariance. Thirdly, I will present Maieutic
> prompting, which improves the logical consistency of neural reasoning by
> integrating with logic structures. I will conclude with future research
> toward more general, grounded, and trustworthy reasoning with language.
>
> *Bio: *Lianhui Qin is a final year PhD student in Paul G. Allen School of
> Computer Science & Engineering at University of Washington, advised by
> Prof. Yejin Choi. Her research interests lie in natural language
> processing, artificial intelligence, and machine learning, with a
> particular focus on natural language reasoning and generation. Her research
> has been recognized with Best Paper Award at NAACL 2022, Best Paper Award
> at WeCNLP 2020, Best Demo Paper Nomination at ACL 2019, as well as
> Microsoft Research PhD Fellowship.
>
>
> *Host: *Matthew Walter <mwalter at ttic.edu>
> <klivescu 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 Sun, Mar 19, 2023 at 3:03 PM Mary Marre <mmarre at ttic.edu> wrote:
>
>> *When:* Monday, March 20, 2023 at* 11:30** a**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=4ae2d7b2-686d-4e3e-aa42-afc40169d0af>*
>> )
>>
>>
>> *Who: * Lianhui Qin, University of Washington
>>
>>
>> ------------------------------
>> *Title: *Constrained, Casual, and Logical Reasoning for Neural
>> Language Generation
>>
>> *Abstract:* Today’s language models (LMs) can produce human-like fluent
>> text. However, they generate words with no grounding in the world and
>> cannot flexibly reason about everyday situations and events, such as
>> counterfactual (“what if?”) and abductive (“what might explain these
>> observations?”) reasoning that are important forms of human cognition
>> activities. In this talk, I will present my research on connecting
>> reasoning with language generation. Reasoning for language generation poses
>> several key challenges, including incorporating diverse contextual
>> constraints on the fly, understanding cause and effect when events unfold,
>> and grounding on logic structures for consistent reasoning. I will first
>> discuss COLD decoding, a unified energy-based framework for any
>> off-the-shelf LMs to reason with arbitrary constraints. It also introduces
>> differentiable reasoning over discrete symbolic text for improved
>> efficiency. Secondly, I will focus on a particularly important form of
>> reasoning, counterfactual reasoning, including its first formulation in
>> language generation and our algorithm, DeLorean, that enables off-the-shelf
>> LMs to capture causal invariance. Thirdly, I will present Maieutic
>> prompting, which improves the logical consistency of neural reasoning by
>> integrating with logic structures. I will conclude with future research
>> toward more general, grounded, and trustworthy reasoning with language.
>>
>> *Bio: *Lianhui Qin is a final year PhD student in Paul G. Allen School
>> of Computer Science & Engineering at University of Washington, advised by
>> Prof. Yejin Choi. Her research interests lie in natural language
>> processing, artificial intelligence, and machine learning, with a
>> particular focus on natural language reasoning and generation. Her research
>> has been recognized with Best Paper Award at NAACL 2022, Best Paper Award
>> at WeCNLP 2020, Best Demo Paper Nomination at ACL 2019, as well as
>> Microsoft Research PhD Fellowship.
>>
>>
>> *Host: *Matthew Walter <mwalter at ttic.edu>
>> <klivescu 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 Mon, Mar 13, 2023 at 5:03 PM Mary Marre <mmarre at ttic.edu> wrote:
>>
>>> *When:* Monday, March 20, 2023 at* 11:30** a**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=4ae2d7b2-686d-4e3e-aa42-afc40169d0af>*
>>> )
>>>
>>>
>>> *Who: * Lianhui Qin, University of Washington
>>>
>>>
>>> ------------------------------
>>> *Title: *Constrained, Casual, and Logical Reasoning for Neural
>>> Language Generation
>>>
>>> *Abstract:* Today’s language models (LMs) can produce human-like fluent
>>> text. However, they generate words with no grounding in the world and
>>> cannot flexibly reason about everyday situations and events, such as
>>> counterfactual (“what if?”) and abductive (“what might explain these
>>> observations?”) reasoning that are important forms of human cognition
>>> activities. In this talk, I will present my research on connecting
>>> reasoning with language generation. Reasoning for language generation poses
>>> several key challenges, including incorporating diverse contextual
>>> constraints on the fly, understanding cause and effect when events unfold,
>>> and grounding on logic structures for consistent reasoning. I will first
>>> discuss COLD decoding, a unified energy-based framework for any
>>> off-the-shelf LMs to reason with arbitrary constraints. It also introduces
>>> differentiable reasoning over discrete symbolic text for improved
>>> efficiency. Secondly, I will focus on a particularly important form of
>>> reasoning, counterfactual reasoning, including its first formulation in
>>> language generation and our algorithm, DeLorean, that enables off-the-shelf
>>> LMs to capture causal invariance. Thirdly, I will present Maieutic
>>> prompting, which improves the logical consistency of neural reasoning by
>>> integrating with logic structures. I will conclude with future research
>>> toward more general, grounded, and trustworthy reasoning with language.
>>>
>>> *Bio: *Lianhui Qin is a final year PhD student in Paul G. Allen School
>>> of Computer Science & Engineering at University of Washington, advised by
>>> Prof. Yejin Choi. Her research interests lie in natural language
>>> processing, artificial intelligence, and machine learning, with a
>>> particular focus on natural language reasoning and generation. Her research
>>> has been recognized with Best Paper Award at NAACL 2022, Best Paper Award
>>> at WeCNLP 2020, Best Demo Paper Nomination at ACL 2019, as well as
>>> Microsoft Research PhD Fellowship.
>>>
>>>
>>> *Host: *Matthew Walter <mwalter at ttic.edu>
>>> <klivescu 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/colloquium/attachments/20230320/e505a972/attachment-0001.html>
More information about the Colloquium
mailing list