Invited Talks

Got feedback? I'm happy to hear about it!
To provide anonymous feedback: Link

The Simpson and Bias Amplification Paradoxes

Presentation

03/2024, Dagstuhl Seminar, Germany ๐Ÿ‡ฉ๐Ÿ‡ช

Whatโ€™s In My Big Data and Its Implications on Models

Presentation

05/2024, IBM Research, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ

05/2024, Bar-Ilan University, Ramat-Gan, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ

05/2024, Technion, Haifa, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ

03/2024, University of Edinburgh, Edinburgh, Scotland ๐Ÿด๓ ง๓ ข๓ ณ๓ ฃ๓ ด๓ ฟ

03/2024, Ludwig Maximilian University of Munich (LMU), Munich, Germany ๐Ÿ‡ฉ๐Ÿ‡ช

02/2024, University of Southern California (USC), Los Angeles, USA ๐Ÿ‡บ๐Ÿ‡ธ

02/2024, University of California Santa Barbara (UCSB), USA ๐Ÿ‡บ๐Ÿ‡ธ

02/2024, University of California Los Angeles (UCLA), USA ๐Ÿ‡บ๐Ÿ‡ธ

11/2023, ร‰cole Polytechnique Fรฉdรฉrale de Lausanne (EPFL), Switzerland ๐Ÿ‡จ๐Ÿ‡ญ

My Intended Dissertation, Itโ€™s (Retrospective) Disruption, And My Current Research

Presentation

04/2023, Georgetown University, DC, USA ๐Ÿ‡บ๐Ÿ‡ธ

Measuring Causal Effects of Data Statistics on Language Model Predictions

Presentation

06/2022, University of Cambridge, UK ๐Ÿ‡ฌ๐Ÿ‡ง

05/2022, University of Copenhagen, Denmark ๐Ÿ‡ฉ๐Ÿ‡ฐ

Causal Attributions in Language Models

Presentation

02/2022, ETH Zรผrich, Switzerland ๐Ÿ‡จ๐Ÿ‡ญ

12/2021, The Hebrew University of Jerusalem, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ

12/2021, New York University (NYU), USA ๐Ÿ‡บ๐Ÿ‡ธ

11/2021, The University of British Columbia (UBC), Vancouver, Canada ๐Ÿ‡จ๐Ÿ‡ฆ

11/2021, AI2, Seattle, USA ๐Ÿ‡บ๐Ÿ‡ธ

11/2021, University of California Irvine (UCI), USA ๐Ÿ‡บ๐Ÿ‡ธ

11/2021, UT Austin, USA ๐Ÿ‡บ๐Ÿ‡ธ

06/2021, University of California Berkeley, USA ๐Ÿ‡บ๐Ÿ‡ธ

04/2021, Carnegie Mellon University (CMU), USA ๐Ÿ‡บ๐Ÿ‡ธ

Complex Commonsense Reasoning & Why We Are Not There Yet

Presentation

03/2021, Future of AI, Keynote speaker

Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals

Presentation

06/2021, IDC Herzliya, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ

02/2021, Google, Seattle, USA ๐Ÿ‡บ๐Ÿ‡ธ

01/2021, reciTAL, Paris, France ๐Ÿ‡ซ๐Ÿ‡ท

Back to Square One: Bias Detection, Training and Commonsense Disentanglement in the Winograd Schema

Presentation

10/2021, ISCOL, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ

12/2020, AI2, Seattle, USA ๐Ÿ‡บ๐Ÿ‡ธ

12/2020, Microsoft, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ

Unsupervised Distillation Of Syntactic Information From Contextualized Word Representations

Presentation

11/2020, Carnegie Mellon University (CMU), USA ๐Ÿ‡บ๐Ÿ‡ธ

Where's My Head? Definition, Dataset and Models for Numeric Fused-Heads Identification and Resolution

Presentation

11/2019, IBM Research, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ

05/2019, Citi Innovation lab, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ

04/2019, Inria Lab, Paris, France ๐Ÿ‡ซ๐Ÿ‡ท

How Large are Lions? Inducing Distributions over Quantitative Attributes

Presentation

01/2020, DataHack, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ

09/2019, ISCOL, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ

03/2019, Excellence student talk, Bar Ilan University, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ

02/2019, University of Pennsylvania, Philadelphia, USA ๐Ÿ‡บ๐Ÿ‡ธ

Adversarial Removal of Demographic Attributes in Machine Learning Systems

Presentation

02/2019, TextKernel, Amsterdam, Netherlands ๐Ÿ‡ณ๐Ÿ‡ฑ

Adversarial Removal of Demographic Attributes from Text Data

Presentation

11/2018, The University Of Sheffield, UK ๐Ÿ‡ฌ๐Ÿ‡ง

11/2018, Imperial College London, UK ๐Ÿ‡ฌ๐Ÿ‡ง

10/2018, PayPal, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ

10/2018, News, Economics and AI Meetup, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ

10/2018, Intuit, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ

10/2018, Microsoft Research, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ

Adversarial Removal of Demographic Attributes in Machine Learning Systems

Presentation

02/2019, TextKernel, Amsterdam, Netherlands ๐Ÿ‡ณ๐Ÿ‡ฑ