Ondrej Dusek
Artificial Intelligence · 2014–2024
A researcher in the Science corpus: 29 papers; trusts 1,477 researchers and is trusted by 375 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 831 citations into it; #1,613 of 36,961 by trust here, #1,687 by citations
- Natural Language Processing — 626 citations into it; #378 of 5,725 by trust here, #383 by citations
- Evaluation & Benchmarks — 270 citations into it; #222 of 3,155 by trust here, #311 by citations
- Computer Vision and Pattern Recognition — 150 citations into it; #4,598 of 21,973 by trust here, #4,771 by citations
- Information Systems — 63 citations into it; #2,098 of 9,233 by trust here, #724 by citations
- Language and Linguistics — 43 citations into it
- Large Language Models — 43 citations into it
- Generative Models — 35 citations into it
Whom Ondrej Dusek trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Philipp Koehn
- Diederik P. Kingma
- Jekaterina Novikova
- Yoshua Bengio
- Alex Graves
- Tsung-Hsien Wen
- Geoffrey E. Hinton
- Ilya Sutskever
- Sepp Hochreiter
- Dzmitry Bahdanau
Who trusts Ondrej Dusek overall
- Sebastian Gehrmann
- Jekaterina Novikova
- Verena Rieser
- Yevgeniy Puzikov
- Mihir Kale
- Craig Thomson
- Elizabeth Clark
- Xiaoyu Shen
- Filip Jurvc'ivcek
- Sheng Shen
Papers from Ondrej Dusek's perspective
Ordered by how strongly the researchers Ondrej Dusek trusts endorse each paper. Same corpus, a different order for every researcher.
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet classification with deep convolutional neural networks
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
- 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)
- ImageNet: A large-scale hierarchical image database
Their papers
- Why We Need New Evaluation Metrics for NLG (2017) — 529 citations
- The E2E Dataset: New Challenges For End-to-End Generation (2017) — 530 citations
- The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics (2021) — 329 citations
- Semantic Noise Matters for Neural Natural Language Generation (2019) — 124 citations
- Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings (2016) — 189 citations
- Findings of the E2E NLG Challenge (2018) — 120 citations
- RankME: Reliable Human Ratings for Natural Language Generation (2018) — 124 citations
- CzEng 1.6: Enlarged Czech-English Parallel Corpus with Processing Tools Dockered (2016) — 97 citations
- GEMv2: Multilingual NLG Benchmarking in a Single Line of Code (2022) — 43 citations
- Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge (2019) — 250 citations
- NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation (2021) — 104 citations
- Alana v2: Entertaining and Informative Open-domain Social Dialogue using Ontologies and Entity Linking (2018) — 54 citations
- Neural Generation for Czech: Data and Baselines (2019) — 22 citations
- Adaptation of machine translation for multilingual information retrieval in the medical domain (2014) — 50 citations
- Multilingual Test Sets for Machine Translation of Search Queries for Cross-Lingual Information Retrieval in the Medical Domain (2014) — 6 citations
- Training a Natural Language Generator From Unaligned Data (2015) — 46 citations
- Alana: Social Dialogue using an Ensemble Model and a Ranker trained on User Feedback (2017) — 45 citations
- Better Conversations by Modeling, Filtering, and Optimizing for Coherence and Diversity (2018) — 66 citations
- One Model, Many Languages: Meta-learning for Multilingual Text-to-Speech (2020) — 62 citations
- Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs (2024) — 339 citations