Ehsan Hosseini-Asl
I am a Senior Deep Learning Scientist at Nvidia AI , working on Large Language Models. Previously, I was a senior research scientist at the Salesforce AI Research. My research area is deep learning with application to natural language processing, speech processing and computer vision.
My current focus is building end-to-end language models for different NLP tasks. Specially, I am interested in building interactive language model which can make conversation with human and accomplish any NLP task. To that end, I proposed SimpleTOD, an end-to-end language model for task oriented dialogue (NeurIPS 2020 Spotlight).
I also work on few-shot learning, and sample efficient deep learning models that generalize better to different domains, including adversarial learning and robust speech recognition.
During PhD, I worked on building interpretable feature learning using non-negativity approach for neural network. This work extend to application in medical image analysis, for segmentation and accurate disease diagnosis models. The application includes lung segmentation, alzheimer's disease, prostate cancer, autism and renal rejection.
During my Master, I started working on neural network. I focused on building a new neural network based on wavelet transform , for learning irregular data, based on their sampling frequencies.
Email /
CV /
GitHub /
Google Scholar /
LinkedIn /
Twitter
|
|
Research
I'm interested in machine learning, deep learning, natural language processing, dialogue, and computer vision.
|
|
Few-shot Aspect-based Sentiment Analysis with generative language model
Ehsan Hosseini-Asl, Wenhao Liu, Caiming Xiong
NAACL, 2022
arxiv /
code /
poster /
slides /
presentation /
Formulating Aspect-Based Sentiment analysis as autoregressive language modeling. It is a multitask model which achieves better few-shot performance with significant smaller standard deviation.
|
|
Joint Energy-based Model Training for Better Calibrated Natural Language Understanding Models
Tianxing He, Bryan McCann, Caming Xiong, Ehsan Hosseini-Asl
EACL, 2021
arxiv /
code /
Using energy-based training (EBM) for fine-tuning language model on NLU tasks. The model reach better calibration with little to no loss in accuracy.
|
|
SimpleTOD: An end-to-end Language model for Task-Orinted Dialogue
Ehsan Hosseini-Asl, Bryan McCann, Chien-Sheng Wu, Semih Yavuz, Richard Socher
NeurIPS Spotlight presentation, 2020
arxiv /
code /
slides /
blog /
presentation /
demo /
Formulating Task-Oriented Dialogue as autoregressive language model. This way, the three subtasks, belief state prediction, action and response generation are modeled jointly.
|
|
Transferable multi-domain state generator for task-oriented dialogue systems
Chien-Sheng Wu, Andrea Madotto, Ehsan Hosseini-Asl, Caiming Xiong, Richard Socher, Pascale Fung
ACL (outstanding paper), 2019
arxiv /
code /
slides /
Proposing an encoder-decoder model for belief state generation in Task-Oriented Dialogue. The model is trained on multiple domains jointly, which achieves better few-shot performance using knowledge share across domains.
|
|
Augmented Cyclic Adversarial learning for low-resource domain adaptation
Ehsan Hosseini-Asl, Yingbo Zhu, Caiming Xiong, Richard Socher
ICLR, 2019
arxiv /
poster /
Augmenting Cyclic adversarial learning algorithm with a more stable cycle consitency loss using source model. This formulation stablize adversarial learning when number of labeled data in target domain is scarce.
|
|
Toward Scalable Neural Dialogue State Tracking Model
Elnaz Nouri, Ehsan Hosseini-Asl
NeurIPS, 2nd Conversational AI workshop, 2018
arxiv /
code /
poster /
We proposed a global RNN encoder for belief state tracking across multiple slots. It improves inference latency by 35\% on average compared to the previous state-of-the-art model (GLAD)
|
|
A Multi-Discriminator CycleGAN for Unsupervised Non-Parallel Speech Domain Adaptation
Ehsan Hosseini-Asl, Yingbo Zhu, Caiming Xiong, Richard Socher
Interspeech, 2018
arxiv /
poster /
blog /
GAN model training on spectrogram is unstable due to complexity in learning distribution of fine-grain frequencies. We propose a multi-frequency band discriminator into GAN model which learn to convert spectrogram from male to female.
|
PhD research
Research on representation learning in deep models. I worked on training a new autoencoder with non-negativity constraint which have better representation learning. This new autoencoder becomes the backbone of algorithms for medical image processing, including image segmentation and disease diagnosis.
|
|
Alzheimer's Disease Diagnostics by a Deeply Supervised Adaptable 3D Convolutional Network
Ehsan Hosseini-Asl, Georgy Gimel'farb, Ayman El-Baz
Frontiers in Biomedicine, 2016
arxiv /
code /
Training a 3D convolutional neural network with deep supervision, improves Alzheimer classification accuracy.
|
|
Alzheimer's Disease Diagnosis by Adaptation of 3D Convolutional Network
Ehsan Hosseini-Asl, Robert Keynton, Ayman El-Baz
ICIP, 2016
arxiv /
code /
Training a 3D convolutional neural network for Alzheimer classification. This network is pretrained with novel greedy layer-wise pretraining.
|
|
3D Lung Segmentation Using Incremental Constrained Nonnegative Matrix Factorization
Ehsan Hosseini-Asl, Jacek M. Zurada, Georgy Gimel'farb, Ayman El-Baz
IEEE, Transactions on Biomedical Engineering (TBME), 2015
arxiv /
An efficient segmentation algorithm based on our previous INMF approach for 3D lung ct scans. It works on voxels instead od pixel.
|
|
Automatic Segmentation of Pathological Lung Using Incremental Nonnegative Matrix Factorization
Ehsan Hosseini-Asl, Jacek M. Zurada, Ayman El-Baz
ICIP, 2015
arxiv /
Our previous NMF-based model requires manual setting of the number of clusters for segmentation. Our new algorithm automatically detects number of clusters in the image, and in-homogeneities.
|
|
Deep Learning of Part-based Representation of Data Using Sparse Autoencoders with Nonnegativity Constraints
Ehsan Hosseini-Asl, Jacek M. Zurada, Ayman El-Baz
IEEE, Transactions on Neural Network and Learning Systems, 2014
arxiv /
code /
Learning part-based features in hidden layers of neural network, by constraining negative weights during training.
|
|
Lung Segmentation Based on Nonnegative Matrix Factorization
Ehsan Hosseini-Asl, Jacek M. Zurada, Ayman El-Baz
ICIP, 2014
arxiv /
Our first algorithm for 3D lung segmentation using Non-negative Matrix Factorization. We treat each pixel and its 3D neighborhood as feature vector in NMF.
|
Other Medical Image Analysis
My phd work on nonnegative-constrained autoencoder (NCAE), results in building several efficient algorithms for image segmentation, feature extraction and disease diagnosis.
|
|
Artificial Intelligence (AI) Accurately Automate And Speed Immunofluorescence (IF)-based Discovery And Validation of Novel Prognostic And Predictive Biomarkers In Prostate Cancer
H. Nguyen, B. Schmidt, E. Hosseini-Asl, C. So, R. Socher, C. Xiong, L. Xue, P. R. Carroll, M. R. Cooperberg
Journal of Urology, 2019
arxiv /
|
|
A New CAD System for Early Diagnosis of Autism Using Structural MRI
M. Ismail, M. Nitzken, A. E. Switala, E. Hosseini-Asl, M. Mahmoud, A. Shalaby, M. Casanova, A. El-Baz
ICIP, 2017
arxiv /
|
|
A comprehensive non-invasive framework for diagnosing prostate cancer
I. Reda, A. Shalaby, M. Elmogy, A. Abou Elfotouha, F. Khalifa, M. Abou El-Ghard, E. Hosseini-Asl, G. Gimel'farb, N. Werghig, A. El-Baz
Computers in biology and medicine, 2017
arxiv /
|
|
A New Non-Invasive Approach for Early Classification of Renal Rejection Types Using Diffusion-Weighted MRI
M. Shehata, F. Khalifa, E. Hollis, A. Soliman, E. Hosseini-Asl, M. Abou El-Ghar, M. El-Baz, A. Dwyer, A. El-Baz, R. Keynton
ICIP, 2016
arxiv /
|
|
Computer-Aided Diagnosis Tool for Early Detection of Prostate Cancer
I. Reda, A. Shalaby, F. Khalifa, M. Elmogy, A. Aboulfotouh, M. Abou El-Ghar, E. Hosseini-Asl, N. Werghi, R. Keynton, A. El-Baz
ICIP, 2016
arxiv /
|
|
A New NMF-Autoencoder Based CAD System For Early Diagnosis of Prostate Cancer
I. Reda, A. Shalaby, F. Khalifa, M. Elmogy, A. Aboulfotouh, M. Abou El-Ghar, E. Hosseini-Asl, N. Werghi, R. Keynton, A. El-Baz
ISBI, 2016
arxiv /
|
MSc. research
Research on combining wavelet transform and neural network. The research results in proposing a neural natwork which can model regression data with different sampling frequencies.
|
|
Nonlinear dynamic system control using wavelet neural network based on sampling theory
Ehsan Hosseini-Asl, Mehdi Shahbazian
IEEE, Intern. Conf. on Systems, Man, and Cybernetics (SMC), 2009
arxiv /
|
|
Non uniform noisy data training using wavelet neural network based on sampling theory
Ehsan Hosseini-Asl, Mehdi Shahbazian, Karim Salahshour
WSEAS Transactions on Systems, 2009
arxiv /
|
|
Wavelet neural network based on sampling theory for non uniform noisy data
Ehsan Hosseini-Asl, Mehdi Shahbazian, Karim Salahshour
WSEAS, 2008
arxiv /
|
|