Sahar Ghannay

Artificial Intelligence · 2018–2021

A researcher in the Science corpus: 2 papers; trusts 15 researchers and is trusted by 4 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 27 citations into it; #25,903 of 35,345 by trust here, #17,110 by citations
• Natural Language Processing — 12 citations into it
• Speech & Audio — 10 citations into it; #794 of 1,076 by trust here, #731 by citations
• Signal Processing — 9 citations into it; #5,491 of 7,572 by trust here, #3,428 by citations
• Model Architectures — 7 citations into it

Whom Sahar Ghannay trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Daniel Povey
2. Vijayaditya Peddinti
3. Anthony Rousseau
4. Alex Graves
5. Hainan Xu
6. Alex Auvolat
7. Jean-Luc Gauvain
8. Timothy Dozat
9. Xuezhe Ma
10. Natalia A. Tomashenko

Who trusts Sahar Ghannay overall

1. Tatiana Likhomanenko
2. Yu Zhang
3. Sasha Luccioni
4. Qiantong Xu
5. Sameer Khurana
6. Max Bain
7. Ngoc-Quan Pham

Papers from Sahar Ghannay's perspective

Ordered by how strongly the researchers Sahar Ghannay trusts endorse each paper. Same corpus, a different order for every researcher.

1. Long Short-Term Memory
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Attention is All you Need (Neural Information Processing Systems)
4. ImageNet classification with deep convolutional neural networks
5. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
6. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
7. Gradient-based learning applied to document recognition
8. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
9. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
10. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)

Their papers

• TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation (2018) — 434 citations
• Evaluating the carbon footprint of NLP methods: a survey and analysis of existing tools (2021) — 111 citations