Hi! I'm Saadia Gabriel.
I'm a final-year PhD candidate in the Paul G. Allen School of Computer Science & Engineering at the University of Washington. I am very fortunate to be advised by Prof. Yejin Choi and Prof. Franziska Roesner. My work focuses on measuring factuality and intent of human-written language. Specifically, I am interested in designing generalizable end-to-end modeling frameworks based upon objectives that are directly aligned with the underlying motivations of a task. Two key dimensions of machine reasoning that excite me are social commonsense reasoning and fairness in NLP. Previously I interned at SRI, in the Mosaic group at AI2 and MSR. I will be applying to faculty positions starting Fall 2022.
New:
October 2022: New paper on testing robustness of NLI and hate speech classifiers with generated adversaries accepted to EMNLP Findings!
August 2022: Guest lecture in UW Intro to Machine Learning course (CSE 416).
July 2022: Named an outstanding reviewer for NAACL 2022.
July 2022: Socio-Cultural Inclusion co-chair for NAACL 2022.
May 2022: Our team's proposal to investigate misinformation and social biases will be part of a new TACC high-performance computing program initative.
April 2022: Invited talk at Cornell JEDI dialogues seminar.
February 2022: Two papers accepted to ACL 2022 main conference!
February 2022: Darpa Semafor keynote talk on Misinfo Reaction Frames.
December 2021: Invited talk at Stanford NLP seminar.
October 2021: Presenting at MIT EECS Rising Stars Workshop.
July 2021: Co-organizing Safety for E2E Conversational AI at SIGDIAL 2021.
May 2021: Work on evaluating effectiveness of factuality metrics for summarization (GO FIGURE) accepted to ACL 2021 Findings!
April 2021: New preprint on defending against misinformation.
January 2021: Invited talk at UMass Amherst Rising Stars Seminar.
December 2020: Paragraph-level Commonsense Transformers accepted to AAAI 2021.
Presenting at NeurIPS 2020 Resistance AI Workshop.
October 2020: Presented on Social and Power Implications of Language at UW colloquium.
September 2020: Presented on summarization with cooperative generator-discriminator networks and detection of implicit social biases in text at BBN Technologies.
July 2020: Presented as part of Voice Tech Global panel on implicit bias towards the Black community and conversational AI.
Preprints
Can Machines Learn Morality? The Delphi Experiment
Liwei Jiang, Jena D. Hwang, Chandra Bhagavatula, Ronan Le Bras, Jenny Liang, Jesse Dodge, Keisuke Sakaguchi, Maxwell Forbes, Jon Borchardt, Saadia Gabriel, Yulia Tsvetkov, Oren Etzioni, Maarten Sap, Regina Rini, Yejin Choi.
ArXiv 2022.
[Preprint]
Conference Papers
NaturalAdversaries: Can Naturalistic Adversaries Be as Effective as Artificial Adversaries?
Saadia Gabriel, Hamid Palangi, Yejin Choi.
EMNLP 2022 Findings.
[Paper]
Misinfo Reaction Frames: Reasoning about Readers’ Reactions to News Headlines
Saadia Gabriel, Skyler Hallinan, Maarten Sap, Pemi Nguyen, Franziska Roesner, Eunsol Choi, Yejin Choi.
ACL 2022.
[Paper][Data/Models]
ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection
Thomas Hartvigsen, Saadia Gabriel, Hamid Palangi, Maarten Sap, Dipankar Ray, Ece Kamar.
ACL 2022.
[Paper][Data/Models]
GO FIGURE: A Meta Evaluation of Factuality in Summarization
Saadia Gabriel, Asli Celikyilmaz, Rahul Jha, Yejin Choi, Jianfeng Gao.
ACL 2021 Findings.
[Paper]
Discourse Understanding and Factual Consistency in Abstractive Summarization
Saadia Gabriel, Antoine Bosselut, Jeff Da, Ari Holtzman, Jan Buys, Kyle Lo, Asli Celikyilmaz, Yejin Choi.
EACL 2021.
[Paper]
Paragraph-level Commonsense Transformers with Recurrent Memory
Saadia Gabriel, Chandra Bhagavatula, Vered Shwartz, Ronan Le Bras, Maxwell Forbes, Yejin Choi.
AAAI 2021.
[Paper] [Project Page]
Detecting and Tracking Communal Bird Roosts in Weather Radar Data
Zezhou Cheng, Saadia Gabriel, Pankaj Bhambhani, Daniel Sheldon, Subhransu Maji, Andrew Laughlin, David Winkler.
AAAI 2020.
[Paper]
The Risk of Racial Bias in Hate Speech Detection
Maarten Sap, Dallas Card, Saadia Gabriel, Yejin Choi, Noah A. Smith.
ACL 2019. Best Paper Nominee.
[Paper]
Early Fusion for Goal Directed Robotic Vision
Aaron Walsman, Yonatan Bisk, Saadia Gabriel, Dipendra Misra, Yoav Artzi, Yejin Choi, Dieter Fox.
IROS 2019. Best Paper Nominee.
[Paper]
I am supported by a ARCS Foundation Fellowship, David Notkin Endowed Graduate Fellowship and a Google-Leap Dissertation Fellowship.