Deborah Cohen
Deborah Cohen received the B.Sc. degree in electrical engineering (summa cum laude) in 2010 and the Ph.D. degree in electrical engineering (signal processing) in 2016 from the Technion - Israel Institute of Technology, Haifa, in 2010. Since 2010, she has been a Project Supervisor with the Signal and Image Processing Lab, the High Speed Digital Systems Lab, the Communications Lab and the Signal Acquisition, Modeling and Processing Lab (SAMPL), at the Electrical Engineering Department, Technion. In 2011, Ms. Cohen was awarded the Meyer Foundation Excellence prize. She received the Sandor Szego Award and the Vivian Konigsberg Award for Excellence in Teaching from 2012 to 2016, the David and Tova Freud and Ruth Freud-Brendel Memorial Scholarship in 2014 and the Muriel and David Jacknow Award for Excellence in Teaching in 2015. Since 2014, Ms. Cohen is an Azrieli Fellow. She is currently a research scientist in the Clair team in Google Israel. Her research interests include theoretical aspects of signal processing, compressed sensing, reinforcement learning and machine learning for dialogues.
Research Areas
Authored Publications
Sort By
AI Increases Global Access to Reliable Flood Forecasts
Asher Metzger
Dana Weitzner
Frederik Kratzert
Guy Shalev
Martin Gauch
Sella Nevo
Shlomo Shenzis
Tadele Yednkachw Tekalign
Vusumuzi Dube
arXiv (2023)
Preview abstract
Floods are one of the most common natural disasters, with a disproportionate impact in developing countries that often lack dense streamflow gauge networks. Accurate and timely warnings are critical for mitigating flood risks, but hydrological simulation models typically must be calibrated to long data records in each watershed. Here we show that AI-based forecasting achieves reliability in predicting extreme riverine events in ungauged watersheds at up to a 5-day lead time that is similar to or better than the reliability of nowcasts (0-day lead time) from a current state of the art global modeling system (the Copernicus Emergency Management Service Global Flood Awareness System). Additionally, we achieve accuracies over 5-year return period events that are similar to or better than current accuracies over 1-year return period events. This means that AI can provide flood warnings earlier and over larger and more impactful events in ungauged basins. The model developed in this paper was incorporated into an operational early warning system that produces publicly available (free and open) forecasts in real time in over 80 countries. This work highlights a need for increasing the availability of hydrological data to continue to improve global access to reliable flood warnings.
View details
Dynamic Composition for Conversational Domain Exploration
Eran Ofek
Sagie Israel Pudinsky
Asaf Revach
Shimi Salant
The Web Conference, ACM (2020), 872–883
Preview abstract
We study conversational domain exploration (CODEX), where the user’s goal is to enrich her knowledge of a given domain by conversing with an informative bot. Such conversations should be well grounded in high-quality domain knowledge as well as engaging and open-ended. A CODEX bot should be proactive and introduce relevant information even if not directly asked for by the user. The bot should also appropriately pivot the conversation to undiscovered regions of the domain. To address these dialogue characteristics, we introduce a novel approach termed dynamic composition that decouples candidate content generation from the flexible composition of bot responses. This allows the bot to control the source, correctness and quality of the offered content, while achieving flexibility via a dialogue manager that selects the most appropriate contents in a compositional manner. We implemented a CODEX bot based on dynamic composition and integrated it into the Google Assistant. As an example domain, the bot conversed about the NBA basketball league in a seamless experience, such that users were not aware whether they were conversing with the vanilla system or the one augmented with our CODEX bot. Results are positive and offer insights into what makes for a good conversation. To the best of our knowledge, this is the first real user experiment of open-ended dialogues as part of a commercial
assistant system.
View details
Preview abstract
Complex classifiers may exhibit ``embarassing'' failures in cases that would be easily classified and justified by a human. Avoiding such failures is obviously paramount, particularly in domains where we cannot accept such unexplained behavior. In this work we focus on one such setting, where a label is perfectly predictable if the input contains certain features, and otherwise, it is predictable by a linear classifier. We define a related hypothesis class and determine its sample complexity.
We also give evidence that efficient algorithms cannot, unfortunately, enjoy this sample complexity. We then derive a simple and efficient algorithm, and also give evidence that its sample complexity is optimal, among efficient algorithms. Experiments on sentiment analysis demonstrate the efficacy of the method, both in terms of accuracy and interpretability.
View details
Sparse imitation learning for text based games with combinatorial action spaces
Chen Tessler
Tom Zahavy
Daniel J. Mankowitz
Shie Mannor
The Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM) (2019)
Preview abstract
We propose a computationally efficient algorithm that combines compressed sensing with imitation learning to solve text-based games with combinatorial action spaces. Specifically, we introduce a new compressed sensing algorithm, named IK-OMP, which can be seen as an extension to the Orthogonal Matching Pursuit (OMP). We incorporate IK-OMP into a supervised imitation learning setting and show that the combined approach (Sparse Imitation Learning, Sparse-IL) solves the entire text-based game of Zork1 with an action space of approximately 10 million actions given both perfect and noisy demonstrations.
View details
