Select a calendar:
Filter February Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for February 01, 2018
-
Six Sigma Green Belt for Process ImprovementThu, Feb 01, 2018
Executive Education
Conferences, Lectures, & Seminars
More Info: https://viterbiexeced.usc.edu/engineering-program-areas/six-sigma-lean-certification/six-sigma-green-belt-process-improvement/
Audiences: Registered Attendees
Contact: Viterbi Professional Programs
-
The Viterbi Career Fair
Thu, Feb 01, 2018 @ 10:00 AM - 03:00 PM
Viterbi School of Engineering Career Connections
Receptions & Special Events
The Viterbi Career Fair is free and open to all students in the USC Viterbi School of Engineering. Students do not need to register for this event, just show up! This casual, yet professional, environment allows students the opportunity to have brief conversations with recruiters about full-time employment, internships, and co-ops. Don't forget your resume!
Location: Trousdale Parkway
Audiences: All Viterbi Students
Contact: RTH 218 Viterbi Career Connections
-
CS Colloquium: Nanyun Peng (University of Southern California) – Jointly Learning Representations for Low Resource Information Extraction
Thu, Feb 01, 2018 @ 11:00 AM - 12:20 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Nanyun Peng , University of Southern California
Talk Title: Jointly Learning Representations for Low Resource Information Extraction
Series: Computer Science Colloquium
Abstract: 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 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.
This lecture satisfies requirements for CSCI 591: Research Colloquium. Please note, due to limited capacity in OHE 100D, seats will be first come first serve.
Biography: Nanyun Peng is a computer scientist at Information Science Institute. She got her Ph.D at Johns Hopkins University. She is broadly interested in Natural Language Processing, Machine Learning, and Information Extraction. Her research focuses on low-resource information extraction, creative language generation, and phonology/morphology modeling. Nanyun is the recipient of the Johns Hopkins University 2016 Fred Jelinek Fellowship. She has a background in computational linguistics and economics and holds BAs in both from Peking University.
Host: David Traum
Location: Olin Hall of Engineering (OHE) - 100D
Audiences: Everyone Is Invited
Contact: Computer Science Department
