Douwe Kiela
Artificial Intelligence · 2014–2024
A researcher in the Science corpus: 53 papers; trusts 3,883 researchers and is trusted by 3,930 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 2,388 citations into it; #363 of 36,961 by trust here, #284 by citations
- Natural Language Processing — 1,533 citations into it; #133 of 5,725 by trust here, #129 by citations
- Computer Vision and Pattern Recognition — 989 citations into it; #1,406 of 21,973 by trust here, #401 by citations
- Evaluation & Benchmarks — 561 citations into it; #510 of 3,155 by trust here, #381 by citations
- Safety, Robustness & Interpretability — 328 citations into it; #506 of 2,259 by trust here, #347 by citations
- Large Language Models — 264 citations into it; #695 of 810 by trust here, #297 by citations
- Multimodal Learning — 244 citations into it; #253 of 1,215 by trust here, #344 by citations
- Representation & Self-Supervised Learning — 243 citations into it; #158 of 3,156 by trust here, #252 by citations
Whom Douwe Kiela trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Kaiming He
- Geoffrey E. Hinton
- Yoshua Bengio
- Ilya Sutskever
- Alex Krizhevsky
- Tomas Mikolov
- Jimmy Ba
- Yann LeCun
- Richard Socher
Who trusts Douwe Kiela overall
- Kurt Shuster
- John Wieting
- Mohit Bansal
- Samuel R. Bowman
- Eric Michael Smith
- Jason Aaron Edward Weston
- Emily Dinan
- Adina Williams
- Yonatan Belinkov
- Alexis Conneau
Papers from Douwe Kiela's perspective
Ordered by how strongly the researchers Douwe Kiela trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- 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
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
Their papers
- Supervised Learning of Universal Sentence Representations from Natural Language Inference Data (2017) — 2,227 citations
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (2020) — 16,110 citations
- Adversarial NLI: A New Benchmark for Natural Language Understanding (2019) — 1,244 citations
- Personalizing Dialogue Agents: I have a dog, do you have pets too? (2018) — 1,727 citations
- SentEval: An Evaluation Toolkit for Universal Sentence Representations (2018) — 695 citations
- True Few-Shot Learning with Language Models (2021) — 532 citations
- Queens Are Powerful Too: Mitigating Gender Bias in Dialogue Generation (2019) — 236 citations
- Retrieval Augmentation Reduces Hallucination in Conversation (2021) — 1,126 citations
- BLOOM: A 176B-Parameter Open-Access Multilingual Language Model (2022) — 2,975 citations
- The Second Conversational Intelligence Challenge (ConvAI2) (2019) — 403 citations
- FLAVA: A Foundational Language And Vision Alignment Model (2021) — 987 citations
- What makes a good conversation? How controllable attributes affect human judgments (2019) — 327 citations
- Dynabench: Rethinking Benchmarking in NLP (2021) — 580 citations
- Unsupervised Question Decomposition for Question Answering (2020) — 206 citations
- Learning to Speak and Act in a Fantasy Text Adventure Game (2019) — 226 citations
- Finding Generalizable Evidence by Learning to Convince Q&A Models (2019) — 40 citations
- Poincaré Embeddings for Learning Hierarchical Representations (2017) — 1,718 citations
- Talk the Walk: Navigating New York City through Grounded Dialogue (2018) — 130 citations
- OBELISC: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents (2023) — 370 citations
- No Training Required: Exploring Random Encoders for Sentence Classification (2019) — 105 citations