News & EventsDepartment Events & Announcements
Events
-
Mar8
EVENT DETAILS
lessAbstract
Scientific papers describe historic and current research progress, and are a rich source of information and ideas. However, a large number of these documents are published every day, overwhelming and leading to information overload for the researchers, clinicians, and decision-makers who read them. Automated approaches leveraging AI and NLP techniques are necessary to unearth the content of these papers while reducing the burden on readers. In this talk, I will present a framework for designing and building applied NLP systems serving biomedical information seeking needs. Specifically, I will discuss two large-scale public data resources that enhance our ability to apply NLP to scientific documents, and two targeted NLP applications that aim to detect evidence for supplement-drug interactions, and assist / automate parts of the systematic review creation process. There are significant challenges to creating useful and functional applied NLP systems, especially in fields like biology or medicine where the outputs of these systems may have direct ramifications on patient behavior and clinical practice.
Biography
Lucy Lu Wang is a postdoctoral investigator at the Allen Institute for Artificial Intelligence, where she works on biomedical applications of NLP and meta-science. She received her PhD in Health Informatics from the University of Washington.
TIME Monday, March 8, 2021 at 12:00 PM - 1:00 PM
CONTACT Pamela Villalovoz pmv@northwestern.edu EMAIL
CALENDAR Department of Computer Science
-
Mar10
EVENT DETAILS
lessAbstract
Over the last several decades, scientists have made strides in understanding the complex processes that define the interaction between our minds and the sounds around us. Even before a sound arrives at the forefront of conscious thought, several cognitive mechanisms are engaged -- our ears present a fundamental re-representation of a sound in time, frequency, and intensity to our brains; we interpret and contextualize sounds through a complicated dynamic between semantics and acoustics; and we may further encode the most salient portions of this information into short-term memory. Some of these processes, particularly at the lowest levels of abstraction relative to a sound wave, are well understood, and are easy to characterize across large sections of the human population; others, however, are the sum of both intuition and observations drawn from small-scale laboratory experiments, and remain as of yet poorly understood.
In this talk, I suggest that there is value in coupling insight into the workings of pre-conscious auditory processing with new frontiers in interface design as a means of unlocking audio technologies that operate in the space of human emotions and experiences over sound objects and events. To do this, I introduce and explore a new research direction focused on the marriage of statistical models of auditory cognition with interface design, termed “Cognitive Audio”. Through the lens of several projects spanning perceptually motivated distance metrics for neural networks and approaches to audio summarization, I discuss the core technical challenges of “probing” a cognitive principle of interest, and constructing scalable-yet-personalized models from sparse, noisy, small-scale datasets built on crowd-sourced data.
Biography
Ishwarya Ananthabhotla is a final year PhD student in the Responsive Environments group at the MIT Media Lab, and received her Bachelors (2015) and Masters (2016) from MIT EECS. Her research interests lie at the intersection of machine learning, signal processing, cognition, and audio. She is a recipient of the NSF Graduate Research Fellowship (2016-2019) and the Apple AI/ML PhD Fellowship (2020), and has interned at Spotify and Facebook Reality Labs during her PhD. Outside of the lab, she is passionate about classical Indian music and performance.
TIME Wednesday, March 10, 2021 at 12:00 PM - 1:00 PM
CONTACT Pamela Villalovoz pmv@northwestern.edu EMAIL
CALENDAR Department of Computer Science
-
Mar12
EVENT DETAILS
lessAbstract
The design of revenue-maximizing auctions with strong incentive guarantees is a core concern of economic theory. Computational auctions enable online advertising, sourcing, spectrum allocation, and myriad financial markets. Analytic progress in this space is notoriously difficult; since Myerson’s 1981 work characterizing single-item optimal auctions, there has been limited progress outside of restricted settings. A recent paper by Dütting et al. circumvents analytic difficulties by applying deep learning techniques to, instead, approximate optimal auctions. Their RegretNet architecture can represent auctions with arbitrary numbers of items and participants; it is trained to be empirically strategyproof, but the property is never exactly verified leaving potential loopholes for market participants to exploit. In parallel, new research from Ilvento et al. and other groups has developed notions of fairness in the context of auction design. Inspired by these advances, in this talk, we discuss extensions of these techniques for approximating auctions using deep learning to address concerns of fairness while maintaining high revenue and strong incentive guarantees; certified robustness, that is, verification of claimed strategyproofness of deep learned auctions; and expressiveness via different demand functions and other constraints.
To enable that last point, we propose a new architecture to learn incentive compatible, revenue-maximizing auctions from sampled valuations, which uses the Sinkhorn algorithm to perform a differentiable bipartite matching. Our new framework allows the network to learn strategyproof revenue-maximizing mechanisms in settings not learnable by the previous RegretNet architecture.This talk covers hot-off-the-presses work led by PhD students Michael Curry, Ping-yeh Chiang, and Samuel Dooley, and undergraduate students Kevin Kuo, Uro Lyi, Anthony Ostuni, and Elizabeth Horishny. Papers have appeared at NeurIPS-20 or are currently under review; please check arXiv or get in touch for drafts.
Biography
John P Dickerson is an Assistant Professor of Computer Science at the University of Maryland as well as co-founder and Chief Scientist of Arthur AI, an enterprise-focused AI/ML model monitoring firm. He is a recipient of awards such as the NSF CAREER Award, IEEE Intelligent Systems AI’s 10 to Watch, Google Faculty Research Award, and paper awards and nominations at venues such as AAAI. His research centers on solving practical economic problems using techniques from computer science, stochastic optimization, and machine learning. He has worked extensively on theoretical and empirical approaches to organ exchange where his work has set policy at the UNOS nationwide kidney exchange; worldwide blood donation markets with Facebook; game-theoretic approaches to counter-terrorism and negotiation, where his models have been deployed; and market design problems in industry (e.g., online advertising) through various startups. Dickerson received his PhD in computer science from Carnegie Mellon University.
TIME Friday, March 12, 2021 at 2:00 PM - 3:00 PM
CONTACT Pamela Villalovoz pmv@northwestern.edu EMAIL
CALENDAR Department of Computer Science
-
Mar13
EVENT DETAILS
lessWinter Classes End
TIME Saturday, March 13, 2021
CONTACT Office of the Registrar nu-registrar@northwestern.edu EMAIL
CALENDAR University Academic Calendar
-
Mar15
EVENT DETAILS
lessWinter Examinations Begin
TIME Monday, March 15, 2021
CONTACT Office of the Registrar nu-registrar@northwestern.edu EMAIL
CALENDAR University Academic Calendar
-
Mar15
EVENT DETAILS
lessAbstract
Artificial Intelligence has made unprecedented progress in the past decade. However, there still remains a large gap between the decision-making capabilities of humans and machines. In this talk, I will investigate two factors to explain why. First, I will discuss the presence of undesirable biases in datasets, which ultimately hurt generalization. I will then present bias mitigation algorithms that boost the ability of AI models to generalize to unseen data. Second, I will explore task-specific prior knowledge which aids robust generalization, but is often ignored when training modern AI architectures. Throughout this discussion, I will focus my attention on language applications, and will show how certain underlying structures can provide useful inductive biases for inferring meaning in natural language. I will conclude with a discussion of how the broader framework of dataset and model biases will play a critical role in the societal impact of AI, going forward.
Biography
Swabha Swayamdipta is a postdoctoral investigator at the Allen Institute for AI, working with Yejin Choi. Her research focuses on natural language processing, where she explores dataset and linguistic structural biases, and model interpretability. Swabha received her Ph.D. from Carnegie Mellon University, under the supervision of Noah A. Smith and Chris Dyer. During most of her Ph.D. she was a visiting student at the University of Washington. She holds a Masters degree from Columbia University, where she was advised by Owen Rambow. Her research has been published at leading NLP and machine learning conferences, and has received an honorable mention for the best paper at ACL 2020.
TIME Monday, March 15, 2021 at 12:00 PM - 1:00 PM
CONTACT Pamela Villalovoz pmv@northwestern.edu EMAIL
CALENDAR Department of Computer Science
-
Mar20
EVENT DETAILS
lessSpring Break Begins
TIME Saturday, March 20, 2021
CONTACT Office of the Registrar nu-registrar@northwestern.edu EMAIL
CALENDAR University Academic Calendar
-
Mar26
EVENT DETAILS
lessWinter Degrees Conferred
TIME Friday, March 26, 2021
CONTACT Office of the Registrar nu-registrar@northwestern.edu EMAIL
CALENDAR University Academic Calendar
-
Mar29
EVENT DETAILS
lessSpring Break Ends
TIME Monday, March 29, 2021
CONTACT Office of the Registrar nu-registrar@northwestern.edu EMAIL
CALENDAR University Academic Calendar
-
Mar30
EVENT DETAILS
lessSpring Classes Begin 8 a.m. Classes remote until Tuesday, April 6.
TIME Tuesday, March 30, 2021
CONTACT Office of the Registrar nu-registrar@northwestern.edu EMAIL
CALENDAR University Academic Calendar