AI-Assisted Knowledge Navigation
By Akhil Arora

Akhil Arora will give a talk on AI-Assisted Knowledge Navigation.

Abstract: Homo sapiens (Latin: “wise human”) is a born knowledge seeker. While modern AI-powered search engines have revolutionized knowledge-seeking by responding to our queries in a manner that resembles natural conversation, systems that understand our knowledge-seeking needs and “take us by the hand” in navigating online knowledge are yet to be realized. In this talk, I will present my vision for the next generation of information systems that assist humans in effectively navigating the deluge of online knowledge.

Specifically, I will present a framework for understanding, modeling, and enhancing human navigation on Wikipedia, the largest platform for open knowledge. First, I will describe an information-theoretic method for understanding the dynamics of human network navigation and present the first large-scale privacy-preserving model for synthesizing human-like navigation traces. Next, I will shed light on knowledge gaps in Wikipedia, describe a framework to assess the causal impact, and present methods for mitigating them in order to improve knowledge navigation on Wikipedia. Finally, I will discuss applications of my work beyond Wikipedia and present exciting future research directions on building multimodal knowledge navigation assistants, designing intuitively navigable information systems, and mitigating multilingual knowledge gaps.

Biography

Akhil Arora is a final year PhD student at the EPFL Data Science Lab advised by Prof. Robert West, and a formal collaborator of the Wikimedia Foundation. Before this, Akhil spent close to five years in the industry working with the research labs of Xerox and American Express as a Research Scientist. The overarching goal of Akhil’s research is to lay a solid foundation for developing the next generation of information systems that assist humans in effectively navigating the deluge of online knowledge. His research has combined techniques from data and network science, natural language processing, machine learning, data management, and causal inference. His work on influence maximization has been recognized as the 8th most influential paper of SIGMOD 2017 by Paper Digest and received the 2018 ACM SIGMOD Most Reproducible Paper Award. He is a recipient of the prestigious EDIC Doctoral Fellowship, an alumnus of the coveted Heidelberg Laureate Forum, and a DAAD AINet fellow on human-centered AI. Additional details are available on his website, https://people.epfl.ch/akhil.arora?lang=en