Program - Confernce Template 2525

Workshop Keynote:

	Information Surgeon
	Heng Ji, University of Illinois at Urbana Champaign, USA
	During crazy times like pandemic, the information released from multiple sources is not only overwhelming in terms of amount, but also misleading in terms of quality. For example, the U.S. Army reservist Maatje Bensassi was falsely accused as the covid-19 coronavirus pandemic's so-called "patient zero", without any evidence. Information pollution often has real-life consequences. Like many others, I had to unfriend or be unfriended by many people due to arguments about the source of coronavirus. Since we cannot fix human's brain, I propose new methods to fix information, namely not only to filter out misinformation/disinformation, but also correct it and generate a correct narrative. Understanding events and communicating about events are fundamental human activities. However, it's much more difficult to remember event-related information compared to entity-related information. For example, most people in the United States will be able to answer the question "Which city is Columbia University is located in?", but very few people can give a complete answer to "Who died from COVID-19?". Human-written history books are often incomplete and highly biased because "History is written by the victors". In this talk I will present a new research direction on event-centric knowledge base construction from multimedia multilingual sources, and then perform consistency checking and reasoning, and then describe the correct information. Our minds represent events at various levels of granularity and abstraction, which allows us to quickly access and reason about old and new scenarios. Progress in natural language understanding and computer vision has helped automate some parts of event understanding but the current, first-generation, automated event understanding is overly simplistic since it is local, sequential and flat. Real events are hierarchical and probabilistic. Understanding them requires knowledge in the form of a repository of abstracted event schemas (complex event templates), understanding the progress of time, using background knowledge, and performing global inference. Our approach to second-generation event understanding builds on an incidental supervision approach to inducing an event schema repository that is probabilistic, hierarchically organized and semantically coherent. Low level primitive components of event schemas are abundant, and can be part of multiple, sparsely occurring, higher-level schemas. Consequently, we combine bottom-up data driven approaches across multiple modalities with top-down consolidation of information extracted from a smaller number of encyclopedic resources. This facilitates inducing higher-level event representations analysts can interact with, and allow them to guide further reasoning and extract events by constructing a novel structured cross-media common semantic space. When complex events unfold in an emergent and dynamic manner, the multimedia multilingual digital data from traditional news media and social media often convey conflicting information. To understand the many facets of such complex, dynamic situations, we have developed various novel methods to induce hierarchical narrative graph schemas and apply them to enhance end-to-end joint neural Information Extraction, event coreference resolution, event time prediction, and knowledge base to natural language generation.
	Heng Ji is a professor at Computer Science Department, and an affiliated faculty member at Electrical and Computer Engineering Department of University of Illinois at Urbana-Champaign. She is also an Amazon Scholar. She received her B.A. and M. A. in Computational Linguistics from Tsinghua University, and her M.S. and Ph.D. in Computer Science from New York University. Her research interests focus on Natural Language Processing, especially on Multimedia Multilingual Information Extraction, Knowledge Base Population and Knowledge-driven Generation. She was selected as "Young Scientist" and a member of the Global Future Council on the Future of Computing by the World Economic Forum in 2016 and 2017. The awards she received include "AI's 10 to Watch" Award by IEEE Intelligent Systems in 2013, NSF CAREER award in 2009, Google Research Award in 2009 and 2014, IBM Watson Faculty Award in 2012 and 2014 and Bosch Research Award in 2014-2018. She was invited by the Secretary of the U.S. Air Force and AFRL to join Air Force Data Analytics Expert Panel to inform the Air Force Strategy 2030. She is the lead of many multi-institution projects and tasks, including the U.S. ARL projects on information fusion and knowledge networks construction, DARPA DEFT Tinker Bell team and DARPA KAIROS RESIN team. She has coordinated the NIST TAC Knowledge Base Population task since 2010. She is the associate editor for IEEE/ACM Transaction on Audio, Speech, and Language Processing, and served as the Program Committee Co-Chair of many conferences including NAACL-HLT2018. She is elected as the North American Chapter of the Association for Computational Linguistics (NAACL) secretary 2020-2021. Her research has been widely supported by the U.S. government agencies (DARPA, ARL, IARPA, NSF, AFRL, DHS) and industry (Amazon, Google, Facebook, Bosch, IBM, Disney).

Workshop Panel:

Operational Value of Narrative Research

On this panel, former and current funding agency program managers will discuss real world values of narrative research, share successful stories and lesson learned from past/ongoing narrative programs, and provide visions for future programs in this domain.

Bill Casebeer, Scientific Systems Company, Inc.

Bill Casebeer is the Senior Director of Human-Machine Systems at Scientific Systems Company, Inc. (SSCI), where he leads teams of scientists and engineers developing new performance-improving concepts in human-autonomy interaction. Prior to joining SSCI, Bill was Director of the Innovation Lab at Beyond Conflict, a non-profit organization dedicated to developing science and technology to prevent conflict and assist in reconciliation, enabling positive social change to happen at scale. Bill was the Senior Research Area Manager in Human Systems and Autonomy for Lockheed Martin’s Advanced Technology Laboratories from 2014-2018, where he led science and technology development programs to improve human performance in multiple domains and to boost the ability of humans and autonomous systems to work together. Bill served as a Program Manager at the Defense Advanced Research Projects Agency from 2010-14 in the Defense Sciences Office and in the Biological Technologies Office, where he managed a digital tutor and other training programs, as well as multiple programs in applied and operational neuroscience and information operations. He retired from active duty as a US Air Force Lieutenant Colonel and intelligence analyst in August 2011 after multiple tours overseas, including working for NATO and being deployed in the Middle East. He holds a Bachelor of Science in political science from the US Air Force Academy, a Master of Arts in national security studies from the Naval Postgraduate School, a Master of Arts in philosophy from the University of Arizona and a joint PhD in cognitive science and philosophy from the University of California at San Diego. His research interests include the intersections of cognitive science and national security policy, neuro-ethics, neural networks, autonomy, political violence, training, autonomy and human performance.

Brian Kettler, DARPA

Dr. Brian Kettler joined the Defense Advanced Research Projects Agency (DARPA) as a Program Manager in the Information Innovation Office (I2O) in March 2019. His research interests include information/influence operations, multi-domain command and control, automated decision support (Artificial Intelligence (AI) reasoning, planning, and machine learning), computational modeling of sociocultural systems, human-machine collaboration, and cognitive science. He is the Program Manager for DARPA's Computational Simulation of Online Social Behavior (SocialSim) program and twenty related small business innovation research (SBIR) and small business technology transfer (STTR) efforts. Dr. Kettler joined DARPA from Lockheed Martin, where he was a Lockheed Martin Fellow and Chief Scientist of the Informatics Lab in the Advanced Technology Labs (ATL). He has been a Principal Investigator for several DARPA, IARPA, and Air Force Research Laboratory efforts developing multi-domain command and control decision aids for military commanders as well as situational understanding and forecasting aids for analysts working with complex operational environments, including pre-conflict competition. Several of his prior programs have transitioned into operational use. Previously he was a Corporate Scientist at ISX Corporation. Kettler has commercial software development experience from work at Brightware, IBM, and Digital Equipment Corporation (DEC). He holds a PhD in Computer Science, with a specialization in AI, from the University of Maryland College Park and a BS in Computer Science from the University of Massachusetts Amherst. He has authored and co-authored papers in AI planning, computational social science, and related areas.

Edward Palazzolo, Army Research Office

Edward T. Palazzolo, Ph.D., is the Program Manager for the Army Research Office's fundamental research program on Social and Cognitive Networks. The goal of the Social and Cognitive Networks program is to understand human behaviors and cognitive processes as part of collective-level phenomena with an emphasis on high performance teams and computational social science. Dr. Palazzolo served on the faculty at The Ohio State University's School of Communication, Arizona State University's Hugh Downs School of Human Communication, and was the Associate Director of the SONIC Research Lab in Industrial Engineering and Management Science at Northwestern University. Dr. Palazzolo has multidisciplinary expertise in the social sciences, leadership, information technology, education, project and program management, business analysis, and coaching. His transactive memory systems research focuses on the interrelations between communication and knowledge networks and their impact on team performance in organizational settings through social network analysis, multilevel modeling, and computational modeling. Beyond research, he is a certified clinical hypnotherapist and a certified facilitator for FranklinCovey with years of experience teaching The 7 Habits of Highly Effective People and Leading at the Speed of Trust.

Jonathan Pfautz, Leidos

Jonathan Pfautz, Chief Scientist at Leidos, guides applied research and development related to understanding and modeling complex human behavior. His research spans AI and machine learning, sensors and sensor processing, modeling and simulation, human factors engineering, and the application of the social and behavioral sciences within computational and data science. Jonathan served as a DARPA program manager from 2015 to 2019. At DARPA, he created and led a program to understand and model online information and misinformation spread - the DARPA Social Simulation (SocialSim) program. While pioneering privacy-protection policies for government research at DARPA, he also led an effort to to understand soldier health outcomes using smartphone data (Warfighter Assessment using Smartphones for Health (WASH)). Jonathan recently edited a 2019 book, Social-Behavioral Modeling for Complex Systems. Prior to DARPA, Dr. Pfautz led cross-disciplinary research to develop and deploy systems at Charles River Analytics, resulting in real-world software systems used by commercial and government partners. Dr. Pfautz has a PhD in computer science from the University of Cambridge and three degrees from MIT: A Master's in computer science and electrical engineering, a BS in brain and cognitive sciences and a BS in computer science and engineering.