Franz Joseph Och
Artificial Intelligence · 1999–2025
A researcher in the Science corpus: 17 papers; trusts 285 researchers and is trusted by 8,679 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 96 citations into it; #122 of 36,961 by trust here, #719 by citations
- Natural Language Processing — 70 citations into it; #29 of 5,725 by trust here, #201 by citations
- Evaluation & Benchmarks — 17 citations into it; #208 of 3,155 by trust here, #998 by citations
- Information Systems — 8 citations into it
- Language and Linguistics — 8 citations into it
- Representation & Self-Supervised Learning — 7 citations into it
- Statistics and Probability — 6 citations into it
Whom Franz Joseph Och trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Peter F. Brown
- Hermann Ney
- Stephan Vogel
- Christoph Tillmann
- Stephen Della Pietra
- Kenji Yamada
- Arthur P. Dempster
- Shankar Kumar
- V. D. Pietra
- I. Dan Melamed
Who trusts Franz Joseph Och overall
- David Chiang
- Ondrej Bojar
- Nadir Durrani
- Jianfeng Gao
- Chris Quirk
- Holger Schwenk
- Philipp Koehn
- Chris Callison-Burch
- Kevin Gimpel
- Jörg Tiedemann
Papers from Franz Joseph Och's perspective
Ordered by how strongly the researchers Franz Joseph Och 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)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
- ImageNet: A large-scale hierarchical image database
- 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)
Their papers
- Statistical Phrase-Based Translation (2003) — 3,951 citations
- Minimum Error Rate Training in Statistical Machine Translation (2003) — 3,328 citations
- A Systematic Comparison of Various Statistical Alignment Models (2003) — 4,656 citations
- Large Language Models in Machine Translation (2007) — 720 citations
- Automatic Evaluation of Machine Translation Quality Using Longest Common Subsequence and Skip-Bigram Statistics (2004) — 927 citations
- The Alignment Template Approach to Statistical Machine Translation (2004) — 1,060 citations
- Discriminative Training and Maximum Entropy Models for Statistical Machine Translation (2002) — 1,234 citations
- Discriminative Reranking for Machine Translation (2004) — 256 citations
- ORANGE: a Method for Evaluating Automatic Evaluation Metrics for Machine Translation (2004) — 426 citations
- Improved Statistical Alignment Models (2000) — 1,193 citations
- A Smorgasbord of Features for Statistical Machine Translation (2004) — 325 citations
- An Efficient Method for Determining Bilingual Word Classes (1999)
- Lattice-based Minimum Error Rate Training for Statistical Machine Translation (2008) — 359 citations
- An Evaluation Tool for Machine Translation: Fast Evaluation for MT Research (2000) — 355 citations
- Unsupervised Morphology Induction Using Word Embeddings (2015) — 153 citations
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities (2025) — 3,609 citations
- No major flaws in “Identification of individuals by trait prediction using whole-genome sequencing data” (2017) — 112 citations