Hello everyone,
You are cordially invited to Ming Zhu's Ph.D. defense
*Title*: Neural Sequence Modeling for Domain-Specific Language Processing:
A Systematic Approach
*Committee*: Dr. Ismini Lourentzou (Co-chair), Dr. Danfeng (Daphne) Yao
(Co-chair), Dr. Edward A. Fox, Dr. Chris Brown, Dr. Wasi Uddin Ahmad
*Date and Time:* Thursday, June 22, 2023, 3:30PM
*Zoom*: https://virginiatech.zoom.us/j/88565467370
<https://www.google.com/url?q=https://virginiatech.zoom.us/j/88565467370&sa=…>
*ABSTRACT*: In recent years, machine learning for natural language
processing (ML4NLP) has made substantial progress in many tasks, including
information retrieval, question answering, information extraction, machine
translation, etc. Benefiting from the highly scalable attention-based
Transformer architecture and enormous open access online data, large-scale
pre-trained language models have shown great modeling and generalization
capacity for sequential data. However, not all domains benefit equally from
the rapid development of ML4NLP. Domains like healthcare and software
engineering have vast amounts of sequential data containing rich knowledge,
yet remain under-explored due to a number of challenges: 1) the
distribution of the sequences in specific domains is different from the
general domain; 2) the effective comprehension of domain-specific data
usually relies on domain knowledge; and 3) the labeled data is usually
scarce and expensive to get in domain-specific settings. In this thesis, we
focus on the research problem of applying ML4NLP methods to address both
common and domain-specific challenges from the healthcare and software
engineering domains. We systematically investigate neural-based machine
learning approaches to address the above challenges in three research
directions: 1) learning with long sequences, 2) learning from domain
knowledge, and 3) learning under limited supervision. Our work can also
potentially benefit more domains with large amounts of sequential data.
Best,
Ismini
--
*Ismini Lourentzou* <https://isminoula.github.io/>
Assistant Professor
Virginia Tech | Computer Science
Email: ilourentzou(a)vt.edu
Good evening everyone,
I hope everyone is having a great summer so far.
Just a friendly reminder that I will be out of the office on the following
dates: June 15 (10a-1p), June 19 (Juneteenth holiday) and July 5-14
(vacation). If you need anything before July 5, please let me know ASAP.
For those who are submitting NSF Career proposals in July, let's try to
have budgets ready by the end of the month, if possible. At this moment,
two faculty members will be submitting Career proposals, if you're planning
to submit, please let me know ASAP (at least I can open up a file in Summit
now).
Thanks as always for your assistance and cooperation. I truly appreciate it.
Regards,
*Joyce I. Newberry, MBAGrant Administrator - Sanghani Center for Artificial
Intelligence & Data Analytics*
Department of Computer Science
Virginia Tech
900 North Glebe Road
Arlington, VA 22203
Phone: (571) 858-3360 | joyce15(a)vt.edu
PLEASE NOTE: I will be out of the office on the following days: June 15
(10a-1p - dentist), June 19th (Juneteenth holiday) and July 5 - 14
(vacation)
*PLEASE NOTE:* OSP requires that you have all the administrative
documents, including accepted and final budget, Approved routing status in
Summit, and complete sponsor forms by 9:00 AM the *day before your proposal
is due*. Please have your complete technical proposal ready to submit, no
later than *9:00 AM the day the proposal is due or we cannot submit*. *Please
see the OSP Procedure 20002 for more details on Proposal Submission*.
https://osp.vt.edu/content/dam/osp_vt_edu/policies/osp20002.pdf
