[Colloquium] Meng Jiang (University of Notre Dame) Effective and Efficient Knowledge-Intensive NLP

[Zainab Aslam]

Department of Computer Science NLP Seminar

Meng Jiang
Assistant Professor of Computer Science and Engineering
University of Notre Dame
Friday, February 17th
10 am
In Person: John Crerar Library 346 and on Zoom

This week we are excited to have Meng Jiang from University of Notre Dame. See you at JCL 346 at 10am or on zoom: https://uchicago.zoom.us/j/98297764499?pwd=ajNQSTZnMHRmMENkd1hjdjlNeW1xdz09<https://urldefense.com/v3/__https:/uchicago.zoom.us/j/98297764499?pwd=ajNQSTZnMHRmMENkd1hjdjlNeW1xdz09__;!!BpyFHLRN4TMTrA!9C9cV2m9j42ujZ3dmka0pw1aBLoxjDLeugyLe1jMB1j3dn2ulWf7gQCRx98AkbcWyaWLFnWx_BwwhDKrRHCKTxc$>.

Meng is visiting us in person and has offered most of his day for meetings. Please sign up to meet him here: https://docs.google.com/spreadsheets/d/1mW7JK8V5Meodeqdxw7WGoVgyZeOS7PzLGnprWJ0-HzE/edit#gid=0<https://urldefense.com/v3/__https:/docs.google.com/spreadsheets/d/1mW7JK8V5Meodeqdxw7WGoVgyZeOS7PzLGnprWJ0-HzE/edit*gid=0__;Iw!!BpyFHLRN4TMTrA!9C9cV2m9j42ujZ3dmka0pw1aBLoxjDLeugyLe1jMB1j3dn2ulWf7gQCRx98AkbcWyaWLFnWx_BwwhDKrm7cErBc$>

Title: Effective and Efficient Knowledge-Intensive NLP
Abstract:
Knowledge-intensive NLP tasks are the tasks that humans could not reasonably be expected to perform without access to external knowledge sources such as Google search, Wikipedia, dictionaries, and knowledge bases. They include open-domain question answering, commonsense reasoning, fact checking, etc. The state-of-the-art performance on such kinds of tasks is usually delivered by knowledge-augmented NLP solutions, named “open-book methods.” They look for useful information (referred as “knowledge”) to infer the output from input. However, the external data are heterogeneous and created independently from the task
input; also, indexing and retrieval are much space and time consuming. In this talk, I will introduce three of our recent work in EMNLP 2022 and ICLR 2023 on effective and efficient knowledge augmentation. Since three conference tutorials in ACL/EMNLP and a successful workshop at AAAI 2023, this area of study has established a growing and enduring community. Please join us!
Bio:
Meng Jiang is an assistant professor in the Department of Computer Science and Engineering at the University of Notre Dame. He is interested in data mining and natural language processing. His data science research focuses on graph and text data for applications such as intelligent assistance, recommender systems, question answering, scientific discovery, and mental healthcare. He received the NSF CAREER award in 2022.

[Image]

Zainab Aslam
Business Assistant – Computer Science
The University of Chicago
5730 S Ellis Ave, JCL 212
Chicago, IL 60637
zaslam at uchicago.edu<mailto:zaslam at uchicago.edu>
Office: 773-702-2166

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20230216/2681d511/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.png
Type: image/png
Size: 77810 bytes
Desc: image001.png
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20230216/2681d511/attachment-0001.png>