Select a calendar:
Filter January Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Conferences, Lectures, & Seminars
Events for January
-
CS Colloquium: Hal Daume (University of Maryland) - Learning Language through Interaction
Mon, Jan 13, 2020 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Hal Daume, University of Maryland
Talk Title: Learning Language through Interaction
Series: CS Colloquium
Abstract: To have the broadest possible positive impact, machine learning-based natural language processing systems must be able to (a) learn when limited training data exists for the target tasks, languages (and varieties), and domains of interest, and (b) identify and mitigate potential harms in their use, in particular arising from the signals on which they are trained. I will first present new algorithms and applications for learning language processing systems through interaction with people, where implicit and/or explicit user feedback drives learning. I will then discuss learning challenges around "fairness" and how such interactive learning mechanisms can help address them.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Hal Daumé III is a Perotto Chair Professor in Computer Science and Language Science at the University of Maryland, and a Senior Principal Researcher at Microsoft Research. His research focuses on developing learning algorithms for natural language processing, with a focus on interactive learning methods, and techniques for mitigating harms that can arise from automated systems. He earned his Ph.D. from the University of Southern California in 2006, was an inaugural diversity and inclusion co-chair at NeurIPS 2018, is an action editor for TACL, and is program co-chair for ICML 2020.
Host: Fei Sha
Location: Ronald Tutor Hall of Engineering (RTH) - 109
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
CS Colloquium: Marine Carpuat (University of Maryland) - Divergences in Neural Machine Translation
Tue, Jan 14, 2020 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Marine Carpuat, University of Maryland
Talk Title: Divergences in Neural Machine Translation
Series: CS Colloquium
Abstract: Despite the explosion of online content worldwide, much information remains isolated by language barriers. While deep neural networks have dramatically improved machine translation (MT), truly breaking language barriers requires not only translating accurately, but also understanding what is said and how it is said across languages. I will first challenge the assumption that translation always preserves meaning, and discuss how to automatically detect when the meaning of a translation diverges from its source. Next, I will show how modeling divergences between MT model hypotheses and reference human translations can improve MT. Finally, I will argue that translation does not necessarily need to preserve all properties of the input and introduce a family of models that let us tailor translation style while preserving input meaning. Taken together, these results illustrate how modeling divergences from common assumptions about translation data can not only improve MT, but also broaden the framing of MT to make it more responsive to user needs.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Marine Carpuat is an Assistant Professor in Computer Science at the University of Maryland. Her research focuses on multilingual natural language processing and machine translation. Before joining the faculty at Maryland, she was a Research Scientist at the National Research Council Canada. She received a PhD in Computer Science and a MPhil in Electrical Engineering from the Hong Kong University of Science & Technology, and a Diplome d'Ingenieur from the French Grande Ecole Supelec. She is the recipient of an NSF CAREER award, research awards from Google and Amazon, best paper awards at *SEM and TALN, and an Outstanding Teaching Award.
Host: Yan Liu
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
CS Colloquium: Arjun Guha (University of Massachusetts Amherst) - New Abstractions for New Programming Platforms
Thu, Jan 16, 2020 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Arjun Guha, University of Massachusetts Amherst
Talk Title: New Abstractions for New Programming Platforms
Series: CS Colloquium
Abstract: Programmers today have to wrestle with a wide variety of programming platforms. However, traditional programming abstractions and tools were designed for an earlier era, and are often ineffective today, e.g., when building scalable cloud services, reliable robot controllers, and robust web applications. To address these kinds of challenges, we need to rethink the abstractions and tools that programmers employ.
In this talk, we first discuss problems that arise in "serverless computing", which is a new approach to cloud computing. We carefully define an operational semantics for serverless computing, which we then use to 1) formulate correctness criteria, 2) design new modularity mechanisms, and 3) develop a serverless computing accelerator that uses language-based sandboxing and speculative optimizations.
Next, we present fundamental limitations of the web programming model, which affect the design of JavaScript, and make it hard to build robust programming tools that run in web browsers. We address this problem by extending JavaScript with first-class continuations, and efficiently compile the extended language to run in unmodified web browsers.
Finally, we present challenges that arise when debugging robot controllers, and why traditional debugging tools do not help. We present an interactive program repair tool, which uses a MAX-SMT solver to search for corrections to a robot state machine, given a small number of human-provided inputs.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Arjun Guha is an associate professor of Computer Science at the University of Massachusetts Amherst. Using the tools and techniques of programming languages, his research addresses security, reliability, and performance problems in web applications, systems, networking, and robotics. His work has received an ACM SIGPLAN Most Influential Paper Award, an ACM SIGPLAN Distinguished Paper Award, an ACM SIGPLAN Research Highlight, and a Google Faculty Research Award.
Host: Ramesh Govindan
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
CS Colloquium: David Pynadath (USC ICT) - Data-Driven Modeling of Human Social Behavior with Recursive Decision-Theoretic Agents
Tue, Jan 21, 2020 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: David Pynadath, USC / ICT
Talk Title: Data-Driven Modeling of Human Social Behavior with Recursive Decision-Theoretic Agents
Abstract: Social scientists, policy makers, and other analysts have increasingly turned to multiagent social simulation as a generative methodology for representing, analyzing, and simulating human behavior. Typical agent-based social simulation methods are attractive, because they use simple, reactive rules that are directly expressible by the people seeking to use them. In contrast, AI provides algorithms for generating autonomous decisions that can match a human level of complexity, but that same complexity is a currently insurmountable obstacle to their use by AI non-experts.
At ICT, we have developed a social simulation framework, PsychSim, using decision-theoretic agents with a theory of mind (ToM) to form mental models about others and use those models to inform their own decision-making. While PsychSim's recursive Partially Observable Markov Decision Processes (POMDPs) offer a generative and transparent approach to social simulation, they share the disadvantage of similarly complex AI languages in that much effort and, often, much error is incurred when building models in them. Fortunately, the growing availability of data about people, their perceptions, and their behaviors offers a novel opportunity for automated support to both reduce the burden and increase the accuracy of the modeling process.
In this talk, I will present algorithms we have developed and applied to two different scenarios: (1) response of an urban population to a disaster, and (2) perceptions of inequality among different national, ethnic, and religious populations. In particular, we analyze the results of applying different automated methods for identifying dynamic influence diagrams whose output matches the beliefs and behaviors that people exhibit in these two scenarios. Because no single model correctly predicted everyone's perceptions and behaviors, we had our algorithm select additional models to capture atypical cases as well. Even with a very restricted space of candidate graphs, our algorithms found multiple models consistent with many of the people in the data sets. We quantify the ambiguity in the models selected by analyzing these cases, and, because of the graphical representation, we can compare models against each other to characterize potential differences in perceptions and behaviors. The result is an automated process that not only generates models for use within multiagent social simulation, but also quantifies the degree of confidence one can place in those models.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Dr. David Pynadath is the Director for Social Simulation Research at USC ICT. He received his Ph.D. from the University of Michigan, Ann Arbor in 1999. He has published papers on multiagent systems, teamwork, social simulation, human-robot interaction, explainable AI, and plan recognition. He is the co-creator and maintainer of PsychSim, the multiagent social simulation framework that was the foundation of the work to be presented. Dr. Pynadath has collaborated with partners in academia and government to apply PsychSim to drive virtual characters in interactive simulations for teaching urban stabilization operations, cross-cultural negotiation, disaster response, and avoiding risky behavior.
Host: Jon May
Location: Ronald Tutor Hall of Engineering (RTH) - 105
Audiences: Everyone Is Invited
Contact: Cherie Carter
-
CAIS Seminar: Nikos Trichakis (MIT) - Data-driven Methods to Improve Organ Allocation for Transplantation
Wed, Jan 22, 2020 @ 04:15 PM - 05:15 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Nikos Trichakis, Massachusetts Institute of Technology
Talk Title: Data-driven Methods to Improve Organ Allocation for Transplantation
Series: USC Center for Artificial Intelligence in Society (CAIS) Seminar Series
Abstract: Current organ distribution and allocation policies have resulted in persistent disparities in access to donated organs for transplantation across different waitlisted candidates based on their geographic location, sex, and/or disease. We discuss a novel optimization scheme that leverages machine learning and simulation techniques to devise allocation policies that could alleviate these disparities and allow for a more efficient use of donated organs in the United States. We find that our proposed allocation policies could provide substantial waitlist mortality reduction (of the order of 20% for end-stage liver disease patients), while providing a more equitable organ access in comparison with other proposals.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Nikos Trichakis is an Associate Professor of Operations Management at the MIT Sloan School of Management. His research interests include optimization under uncertainty, data-driven optimization and analytics, with application in healthcare, supply chain management, and finance. Trichakis is also interested in the interplay of fairness and efficiency in resource allocation problems and operations, and the inherent tradeoffs that arise in balancing these objectives.
Host: USC Center for Artificial Intelligence in Society (CAIS)
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Colloquium: Nanyun Peng (USC / ISI) - From Language Understanding to Creative Generation
Thu, Jan 23, 2020 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Nanyun Peng, USC / ISI
Talk Title: From Language Understanding to Creative Generation
Series: CS Colloquium
Abstract: Recent advances in data-driven approaches have demonstrated appealing results in generating natural languages in applications like machine translation and summarization. However, when the generation tasks are open-ended and the content is under-specified, existing techniques struggle to generate coherent and creative sentences. This happens because the generation models are trained to capture the surface form (i.e. sequences of words), rather than the underlying semantics and discourse structures. Moreover, composing creative pieces such as puns, poems, and stories require deviating from the norm, whereas existing generation approaches seek to mimic the norm and thus are unlikely to lead to truly novel, creative composition. In this talk, I will present several of our recent works related to creative story and pun generation, emphasizing the importance of understanding and control for creative generation.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Nanyun Peng is a Research Assistant Professor of Computer Science at the University of Southern California, and a Research Lead at the Information Sciences Institute. She received a Ph.D. in Computer Science from Johns Hopkins University. Her research focuses on creative language generation, and the robustness and generalizability of natural language understanding, with works being featured in major tech media such as Wired and The Register. Nanyun received a Google Anita Borg Scholarship, a Fred Jelinek Fellowship, and multiple DARPA, IARPA, and NIH grants. She has backgrounds in Linguistics and Economics and held BAs in both.
Host: Xiang Ren
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
CS Distinguished Lecture: Manuela Veloso (JP Morgan) - AI for Intelligent Financial Services: Examples and Discussion
Thu, Jan 23, 2020 @ 04:00 PM - 05:20 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Manuela Veloso, JPMorgan AI Research, on leave: Herbert A. Simon University Professor School of Computer Science, Carnegie Mellon University
Talk Title: AI for Intelligent Financial Services: Examples and Discussion
Series: Computer Science Distinguished Lecture Series
Abstract: After more than 30 years in academia researching in the area of AI, as a student and as a faculty, I joined JPMorgan to create and head an AI research group. In this talk, I will present several concrete examples of the projects we are pursuing in engagement with the lines of business. I will focus on areas related to data, learning from experience, explainability, and ethics. I will conclude with a discussion of my current understanding of the transformational impact that AI can have in the future of financial services.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Manuela M. Veloso is the Head of J.P. Morgan AI Research, which pursues fundamental research in areas of core relevance to financial services, including data mining and cryptography, machine learning, explainability, and human-AI interaction. J.P. Morgan AI Research partners with applied data analytics teams across the firm as well as with leading academic institutions globally.
Professor Veloso is on leave from Carnegie Mellon University as the Herbert A. Simon University Professor in the School of Computer Science, and the past Head of the Machine Learning Department. With her students, she had led research in AI, with a focus on robotics and machine learning, having concretely researched and developed a variety of autonomous robots, including teams of soccer robots, and mobile service robots. Her robot soccer teams have been RoboCup world champions several times, and the CoBot mobile robots have autonomously navigated for more than 1,000km in university buildings.
Professor Veloso is the Past President of AAAI, (the Association for the Advancement of Artificial Intelligence), and the co-founder, Trustee, and Past President of RoboCup. Professor Veloso has been recognized with a multiple honors, including being a Fellow of the ACM, IEEE, AAAS, and AAAI. She is the recipient of several best paper awards, the Einstein Chair of the Chinese Academy of Science, the ACM/SIGART Autonomous Agents Research Award, an NSF Career Award, and the Allen Newell Medal for Excellence in Research.
Professor Veloso earned a Bachelor and Master of Science degrees in Electrical and Computer Engineering from Instituto Superior Tecnico in Lisbon, Portugal, a Master of Arts in Computer Science from Boston University, and Master of Science and PhD in Computer Science from Carnegie Mellon University. See www.cs.cmu.edu/~mmv/Veloso.html for her scientific publications.
Host: Maja Mataric and Heather Culbertson
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
