no code implementations • EMNLP (sustainlp) 2021 • Saleh Soltan, Haidar Khan, Wael Hamza
We demonstrate that in contradiction to the previous observation in the case of monolingual distillation, in multilingual settings, distillation during pretraining is more effective than distillation during fine-tuning for zero-shot transfer learning.
no code implementations • 5 Mar 2022 • Weiqi Sun, Haidar Khan, Nicolas Guenon des Mesnards, Melanie Rubino, Konstantine Arkoudas
We examine two such promising techniques, prefix tuning and bias-term tuning, specifically on semantic parsing.
no code implementations • 2 Feb 2022 • Liyan Xu, Yile Gu, Jari Kolehmainen, Haidar Khan, Ankur Gandhe, Ariya Rastrow, Andreas Stolcke, Ivan Bulyko
Specifically, training a bidirectional model like BERT on a discriminative objective such as minimum WER (MWER) has not been explored.
Automatic Speech Recognition
Natural Language Understanding
+1
no code implementations • 8 Jul 2021 • Daniel Park, Haidar Khan, Azer Khan, Alex Gittens, Bülent Yener
Adversarial examples pose a threat to deep neural network models in a variety of scenarios, from settings where the adversary has complete knowledge of the model in a "white box" setting and to the opposite in a "black box" setting.
no code implementations • ICON 2020 • Charith Peris, Gokmen Oz, Khadige Abboud, Venkata sai Varada, Prashan Wanigasekara, Haidar Khan
For IC and NER multi-task experiments, when evaluating on the mismatched test set, we see improvements across all domains in German and in 17 out of 19 domains in Portuguese (improvements based on change in SeMER scores).
Abstractive Text Summarization
Automatic Speech Recognition
+5
no code implementations • Findings of the Association for Computational Linguistics 2020 • Prafull Prakash, Saurabh Kumar Shashidhar, Wenlong Zhao, Subendhu Rongali, Haidar Khan, Michael Kayser
The current state-of-the-art task-oriented semantic parsing models use BERT or RoBERTa as pretrained encoders; these models have huge memory footprints.
no code implementations • CONLL 2020 • Qile Zhu, Haidar Khan, Saleh Soltan, Stephen Rawls, Wael Hamza
For complex parsing tasks, the state-of-the-art method is based on autoregressive sequence to sequence models to generate the parse directly.
no code implementations • 15 Nov 2019 • Michael P. Perrone, Haidar Khan, Changhoan Kim, Anastasios Kyrillidis, Jerry Quinn, Valentina Salapura
This paper presents a methodology for selecting the mini-batch size that minimizes Stochastic Gradient Descent (SGD) learning time for single and multiple learner problems.
no code implementations • ICLR 2020 • Haidar Khan, Daniel Park, Azer Khan, Bülent Yener
Adversarial examples pose a threat to deep neural network models in a variety of scenarios, from settings where the adversary has complete knowledge of the model and to the opposite "black box" setting.
no code implementations • 23 May 2019 • Haidar Khan, Lara Marcuse, Bülent Yener
In this work, we propose new objective functions to train deep neural network based density ratio estimators and apply it to a change point detection problem.
no code implementations • 9 Apr 2019 • Daniel Park, Haidar Khan, Bülent Yener
There has been an increased interest in the application of convolutional neural networks for image based malware classification, but the susceptibility of neural networks to adversarial examples allows malicious actors to evade classifiers.
1 code implementation • NeurIPS 2018 • Haidar Khan, Bulent Yener
Our results show that the WD layer can improve neural network based time series classifiers both in accuracy and interpretability by learning directly from the input signal.
no code implementations • 29 May 2018 • Haidar Khan, Lara Marcuse, Madeline Fields, Kalina Swann, Bülent Yener
Significance: We demonstrate that a robust set of features can be learned from scalp EEG that characterize the preictal state of focal seizures.