no code implementations • NAACL 2022 • Sarah Alnegheimish, Alicia Guo, Yi Sun
Evaluation of biases in language models is often limited to synthetically generated datasets.
no code implementations • 30 Jan 2024 • Lei Xu, Sarah Alnegheimish, Laure Berti-Equille, Alfredo Cuesta-Infante, Kalyan Veeramachaneni
Experimental results on 4 datasets and BERT and distilBERT classifiers show that SP-Defense improves \r{ho} by 14. 6% and 13. 9% and decreases the attack success rate of SP-Attack by 30. 4% and 21. 2% on two classifiers respectively, and decreases the attack success rate of existing attack methods that involve multiple-word perturbations.
1 code implementation • 26 Oct 2023 • Sarah Alnegheimish, Laure Berti-Equille, Kalyan Veeramachaneni
The framework provides universal abstractions to represent models, extensibility to add new pipelines and datasets, hyperparameter standardization, pipeline verification, and frequent releases with published benchmarks.
3 code implementations • 27 Dec 2022 • Lawrence Wong, Dongyu Liu, Laure Berti-Equille, Sarah Alnegheimish, Kalyan Veeramachaneni
We then propose AER (Auto-encoder with Regression), a joint model that combines a vanilla auto-encoder and an LSTM regressor to incorporate the successes and address the limitations of each method.
1 code implementation • 12 May 2022 • Sarah Alnegheimish, Alicia Guo, Yi Sun
Evaluation of biases in language models is often limited to synthetically generated datasets.
2 code implementations • 19 Apr 2022 • Sarah Alnegheimish, Dongyu Liu, Carles Sala, Laure Berti-Equille, Kalyan Veeramachaneni
The detection of anomalies in time series data is a critical task with many monitoring applications.
no code implementations • 5 Apr 2021 • Fahad Alhasoun, Sarah Alnegheimish, Joshua Tenenbaum
Recent findings suggest that humans deploy cognitive mechanism of physics simulation engines to simulate the physics of objects.
3 code implementations • 1 Oct 2020 • Sarah Alnegheimish, Najat Alrashed, Faisal Aleissa, Shahad Althobaiti, Dongyu Liu, Mansour Alsaleh, Kalyan Veeramachaneni
An estimated 180 papers focusing on deep learning and EHR were published between 2010 and 2018.
5 code implementations • 16 Sep 2020 • Alexander Geiger, Dongyu Liu, Sarah Alnegheimish, Alfredo Cuesta-Infante, Kalyan Veeramachaneni
However, detecting anomalies in time series data is particularly challenging due to the vague definition of anomalies and said data's frequent lack of labels and highly complex temporal correlations.