Hi! I'm Saadia Gabriel.

I'm a third-year PhD student in the Paul G. Allen School of Computer Science & Engineering at the University of Washington. I am advised by Prof. Yejin Choi. My research area is natural language understanding and generation. I'm excited about machine learning techniques and deep-learning models for social commonsense and logical reasoning in text.

New: Social Bias Frames preprint on arXiv

"Detecting and Tracking Communal Bird Roosts in Weather Radar Data" accepted to AAAI 2020

Recent Projects:

Coherent Text Generation with Narrative Flow:

Cooperative Generator-Discriminator Networks
for Abstractive Summarization with Narrative Flow

Saadia Gabriel, Antoine Bosselut, Ari Holtzman, Kyle Lo, Asli Celikyilmaz, Yejin Choi. arXiv preprint 2019.

Read More

Toxic Language Detection in Social Media:

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.

Read More

Interpretable Question-Answering and Generation:

MathQA: Towards Interpretable Math Word Problem Solving
with Operation-Based Formalisms

Aida Amini, Saadia Gabriel, Shanchuan Lin,
Rik Koncel-Kedziorski, Yejin Choi, Hannaneh Hajishirzi.
NAACL 2019. Check out the dataset and leaderboard!

Read More

ML for Vision, Robotics and Social Impact:

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.

Read More

Ruling the Roost with CNNs: Detecting and Tracking Communal Bird Roosts in Weather Radar Data

Zezhou Cheng, Saadia Gabriel, Pankaj Bhambhani,
Daniel Sheldon, Subhransu Maji, Andrew Laughlin, David Winkler.
Fine-Grained Visual Categorization Workshop (FGVC5) at CVPR 2018.

Read More