The Simpson and Bias Amplification Paradoxes
Presentation
03/2024, Dagstuhl Seminar, Germany ๐ฉ๐ช
Whatโs In My Big Data and Its Implications on Models
Presentation05/2024, IBM Research, Israel ๐ฎ๐ฑ
05/2024, Bar-Ilan University, Ramat-Gan, Israel ๐ฎ๐ฑ
05/2024, Technion, Haifa, Israel ๐ฎ๐ฑ
03/2024, University of Edinburgh, Edinburgh, Scotland ๐ด๓ ง๓ ข๓ ณ๓ ฃ๓ ด๓ ฟ
03/2024, Ludwig Maximilian University of Munich (LMU), Munich, Germany ๐ฉ๐ช
02/2024, University of Southern California (USC), Los Angeles, USA ๐บ๐ธ
02/2024, University of California Santa Barbara (UCSB), USA ๐บ๐ธ
02/2024, University of California Los Angeles (UCLA), USA ๐บ๐ธ
11/2023, รcole Polytechnique Fรฉdรฉrale de Lausanne (EPFL), Switzerland ๐จ๐ญ
My Intended Dissertation, Itโs (Retrospective) Disruption, And My Current Research
Presentation
04/2023, Georgetown University, DC, USA ๐บ๐ธ
Measuring Causal Effects of Data Statistics on Language Model Predictions
Presentation
06/2022, University of Cambridge, UK ๐ฌ๐ง
05/2022, University of Copenhagen, Denmark ๐ฉ๐ฐ
Causal Attributions in Language Models
Presentation
02/2022, ETH Zรผrich, Switzerland ๐จ๐ญ
12/2021, The Hebrew University of Jerusalem, Israel ๐ฎ๐ฑ
12/2021, New York University (NYU), USA ๐บ๐ธ
11/2021, The University of British Columbia (UBC), Vancouver, Canada ๐จ๐ฆ
11/2021, AI2, Seattle, USA ๐บ๐ธ
11/2021, University of California Irvine (UCI), USA ๐บ๐ธ
11/2021, UT Austin, USA ๐บ๐ธ
06/2021, University of California Berkeley, USA ๐บ๐ธ
04/2021, Carnegie Mellon University (CMU), USA ๐บ๐ธ
Complex Commonsense Reasoning & Why We Are Not There Yet
Presentation03/2021, Future of AI, Keynote speaker
Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals
Presentation06/2021, IDC Herzliya, Israel ๐ฎ๐ฑ
02/2021, Google, Seattle, USA ๐บ๐ธ
01/2021, reciTAL, Paris, France ๐ซ๐ท
Back to Square One: Bias Detection, Training and Commonsense Disentanglement in the Winograd Schema
Presentation10/2021, ISCOL, Israel ๐ฎ๐ฑ
12/2020, AI2, Seattle, USA ๐บ๐ธ
12/2020, Microsoft, Israel ๐ฎ๐ฑ
Unsupervised Distillation Of Syntactic Information From Contextualized Word Representations
Presentation
11/2020, Carnegie Mellon University (CMU), USA ๐บ๐ธ
Where's My Head? Definition, Dataset and Models for Numeric Fused-Heads Identification and Resolution
Presentation11/2019, IBM Research, Israel ๐ฎ๐ฑ
05/2019, Citi Innovation lab, Israel ๐ฎ๐ฑ
04/2019, Inria Lab, Paris, France ๐ซ๐ท
How Large are Lions? Inducing Distributions over Quantitative Attributes
Presentation01/2020, DataHack, Israel ๐ฎ๐ฑ
09/2019, ISCOL, Israel ๐ฎ๐ฑ
03/2019, Excellence student talk, Bar Ilan University, Israel ๐ฎ๐ฑ
02/2019, University of Pennsylvania, Philadelphia, USA ๐บ๐ธ
Adversarial Removal of Demographic Attributes in Machine Learning Systems
Presentation02/2019, TextKernel, Amsterdam, Netherlands ๐ณ๐ฑ
Adversarial Removal of Demographic Attributes from Text Data
Presentation11/2018, The University Of Sheffield, UK ๐ฌ๐ง
11/2018, Imperial College London, UK ๐ฌ๐ง
10/2018, PayPal, Israel ๐ฎ๐ฑ
10/2018, News, Economics and AI Meetup, Israel ๐ฎ๐ฑ
10/2018, Intuit, Israel ๐ฎ๐ฑ
10/2018, Microsoft Research, Israel ๐ฎ๐ฑ