Mirela-Stefania Duma

Natural Language Processing · 2016–2017

A researcher in the Science corpus: 2 papers; trusts 32 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Natural Language Processing — 22 citations into it
• Artificial Intelligence — 16 citations into it
• Representation & Self-Supervised Learning — 7 citations into it
• Evaluation & Benchmarks — 6 citations into it

Whom Mirela-Stefania Duma trusts overall

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

1. Tomas Mikolov
2. Quoc V. Le
3. Franz Joseph Och
4. Andreas Stolcke
5. Jörg Tiedemann
6. Kenneth Heafield
7. Philipp Koehn
8. Radim Rehurek
9. Reinhard Kneser
10. Yoshua Bengio

Papers from Mirela-Stefania Duma's perspective

Ordered by how strongly the researchers Mirela-Stefania Duma trusts endorse each paper. Same corpus, a different order for every researcher.

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

Their papers

• SEF@UHH at SemEval-2017 Task 1: Unsupervised Knowledge-Free Semantic Textual Similarity via Paragraph Vector (2017) — 9 citations
• Data Selection for IT Texts using Paragraph Vector (2016) — 6 citations