SHANTI at the University of Virginia

News / Latest Posts

3/27/17: CS Speaker: Nanyun Peng

violetpengcroppedThe UVa Department of Computer Science presents:


Speaker: Nanyun Peng

Date: Monday March 27, 2017

Time: 10:45am

Location: Rice Hall, Room 242

Title: Representation Learning with Joint Models for Information Extraction



There is abundant knowledge out there carried in the form of natural language texts, such as social media posts, scientific research literature, medical records, etc., which grows at an astonishing rate. Yet this knowledge is mostly inaccessible to computers and overwhelming for human experts to absorb. Information extraction (IE) processes raw texts to produce machine understandable structured information, thus dramatically increasing the accessibility of knowledge through search engines, interactive AI agents, and medical research tools. However, traditional IE systems assume abundant human annotations for training high quality machine learning models, which is impractical when trying to deploy IE systems to a broad range of domains, settings and languages. In this talk, I will present how to use deep representation learning to leverage the distributional statistics of characters and words, the annotations for other tasks and other domains, and the linguistics and problem structures, to combat the problem of inadequate supervision, and conduct information extraction with scarce human annotations.


Nanyun Peng is a PhD candidate in the Department of Computer Science at Johns Hopkins University, affiliated with the Center for Language and Speech Processing and advised by Dr. Mark Dredze. She is broadly interested in Natural Language Processing, Machine Learning, and Information Extraction. Her research focuses on using deep learning for information extraction with scarce human annotations. Nanyun is the recipient of the Johns Hopkins University 2016 Fred Jelinek Fellowship. She has completed two research internships at IBM T.J. Watson Research Center, and Microsoft Research Redmond. She holds a master’s degree in Computer Science and BAs in Computational Linguistics and Economics, all from Peking University.

Matt Kirschenbaum | DH@UVa | March 20



“Greenscreeners: Locating the Literary History of Word Processing”

Matthew Kirschenbaum
Associate Professor, English, University of Maryland and
Associate Director, Maryland Institute for Technology
in the Humanities (MITH)

Monday, March 20, 4:00p

Brooks Hall Commons

REGISTER HERE for DH Mixer Afterward

For more information, click here.

IATH 2017 Call for Fellows

IATH is looking for applications for 2017-2018 Residential and Associate Fellows. University of Virginia faculty members involved in humanities research through any department are eligible to apply. Non-UVA faculty can apply for Visiting Fellowships. The deadline is February 28, 2017. We strongly encourage interested applicants to contact IATH Director Worthy Martin to discuss their proposals; please call 924-4527 to schedule an appointment. More information and guidelines can be found at

IATH_poster_2017 copy










Click on image to enlarge it.

Data Science Presidential Fellows Bring Life to Data Research, and Vice Versa

In the News: UVa Data Science Institute‘s Presidential Fellows in Data Science. Founded three years ago, the Data Science Institute has been working to create opportunities for cross-Grounds collaboration in “big data” research. Graduate students across the disciplines are currently working together to resolve real-world problems by finding data-driven solutions.

To read more about these interesting projects, click here.

UVA Researchers Embark on Endless Pursuits

Daniel Pitti’s (Associate Director, IATH) ongoing database project - Social Networks and Archival Context project – is in the news. “Creating an International Database of Historical Social Networks” is one of five exciting, long-range research projects being carried on at UVa presented in this current UVaToday article.

For the complete article, click here.