Ankur Bapna
Artificial Intelligence · 2018–2025
A researcher in the Science corpus: 33 papers; trusts 1,631 researchers and is trusted by 158 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,176 citations into it; #2,645 of 36,961 by trust here, #1,492 by citations
- Natural Language Processing — 590 citations into it; #703 of 5,725 by trust here, #403 by citations
- Computer Vision and Pattern Recognition — 442 citations into it; #4,007 of 21,973 by trust here, #2,088 by citations
- Speech & Audio — 232 citations into it; #989 of 1,080 by trust here, #384 by citations
- Evaluation & Benchmarks — 173 citations into it
- Signal Processing — 163 citations into it; #7,503 of 7,592 by trust here, #3,788 by citations
- Model Architectures — 162 citations into it
- Representation & Self-Supervised Learning — 150 citations into it
Whom Ankur Bapna trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yoshua Bengio
- Ilya Sutskever
- Diederik P. Kingma
- Geoffrey E. Hinton
- Alex Graves
- Jimmy Ba
- Alex Krizhevsky
- Noam Shazeer
- Kaiming He
- Kyunghyun Cho
Who trusts Ankur Bapna overall
- Jonas Pfeiffer
- Orhan Firat
- Naveen Arivazhagan
- Sneha Kudugunta
- Biao Zhang
- Ye Jia
- Yu Zhang
- Xian Li
- Sebastian Ruder
- Roee Aharoni
Papers from Ankur Bapna's perspective
Ordered by how strongly the researchers Ankur Bapna trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- ImageNet classification with deep convolutional neural networks
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
Their papers
- The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation (2018) — 479 citations
- Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges (2019) — 477 citations
- Simple, Scalable Adaptation for Neural Machine Translation (2019) — 459 citations
- Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling (2019) — 215 citations
- Evaluating the Cross-Lingual Effectiveness of Massively Multilingual Neural Machine Translation (2019) — 76 citations
- Building Machine Translation Systems for the Next Thousand Languages (2022) — 120 citations
- Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets (2021) — 356 citations
- Scaling Laws for Neural Machine Translation (2021) — 136 citations
- Training Deeper Neural Machine Translation Models with Transparent Attention (2018) — 147 citations
- mSLAM: Massively multilingual joint pre-training for speech and text (2022) — 133 citations
- Investigating Multilingual NMT Representations at Scale (2019) — 138 citations
- Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translation (2020) — 88 citations
- FLEURS: FEW-Shot Learning Evaluation of Universal Representations of Speech (2022) — 651 citations
- MAESTRO: Matched Speech Text Representations through Modality Matching (2022) — 125 citations
- Revisiting Character-Based Neural Machine Translation with Capacity and Compression (2018) — 101 citations
- The Missing Ingredient in Zero-Shot Neural Machine Translation (2019) — 123 citations
- Language ID in the Wild: Unexpected Challenges on the Path to a Thousand-Language Web Text Corpus (2020) — 112 citations
- Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model (2019) — 194 citations
- SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training (2021) — 102 citations
- Building a Conversational Agent Overnight with Dialogue Self-Play (2018) — 208 citations