Franz Josef Och joined Google in 2004 as a research scientist, where he leads the machine translation group. He has been working on statistical machine translation since 1997.
Franz worked as a Research Scientist at the Information Sciences Institute at the University of Southern California from 2002 to 2004. His main research interests are statistical machine translation, natural language processing and machine learning. He has co-authored more than fifty scientific papers and has written several open-source software packages related to statistical natural language processing.
He received a PhD in Computer Science at the RWTH Aachen, Germany in 2002 and his Diploma Degree in Computer Science at the University of Erlangen-Nuremberg, Germany in 1998.
Efficient Minimum Error Rate Training and Minimum Bayes-Risk Decoding for Translation Hypergraphs and Lattices, Shankar Kumar, Wolfgang Macherey, Chris Dyer, Franz Och, Proceedings of the 47th Annual Meeting of the ACL and the 4th IJCNLP of the AFNLP, 2009, pp. 163-171.
A systematic comparison of phrase-based, hierarchical and syntax-augmented statistical MT, Andreas Zollmann, Ashish Venugopal, Franz Josef Och, Jay Ponte, Proceedings of the 22nd International Conference on Computational Linguistics (COLING), 2008 (to appear).
Lattice Minimum Bayes-Risk Decoding for Statistical Machine Translation, Roy Tromble, Shankar Kumar, Franz Och, Wolfgang Macherey, Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pp. 620-629.
Lattice-based Minimum Error Rate Training for Statistical Machine Translation, Wolfgang Macherey, Franz Och, Ignacio Thayer, Jakob Uszkoreit, Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 725-734.
An Empirical Study on Computing Consensus Translations from Multiple Machine Translation Systems, Wolfgang Macherey, Franz J. Och, Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pp. 986-995.
Improving Word Alignment with Bridge Languages, Shankar Kumar, Franz Och, Wolfgang Macherey, Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, 2007.
Large Language Models in Machine Translation, Thorsten Brants, Ashok C. Popat, Peng Xu, Franz J. Och, Jeffrey Dean, Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pp. 858-867.
Automatic Evaluation of Machine Translation Quality Using Longest Common Subsequence and Skip-Bigram Statistics, Chin-Yew Lin, Franz Josef Och, ACL, 2004, pp. 605-612.
Discriminative Reranking for Machine Translation, Libin Shen, Anoop Sarkar, Franz Josef Och, HLT-NAACL, 2004, pp. 177-184.
The Alignment Template Approach to Statistical Machine Translation, Franz Josef Och, Hermann Ney, Computational Linguistics, vol. 30 (2004), pp. 417-449.
A Systematic Comparison of Various Statistical Alignment Models, Franz Josef Och, Hermann Ney, Computational Linguistics, vol. 29 (2003), pp. 19-51.
Comparison of Alignment Templates and Maximum Entropy Models for NLP, Oliver Bender, Klaus Macherey, Franz Josef Och, Hermann Ney, EACL, 2003, pp. 11-18.
Efficient Search for Interactive Statistical Machine Translation, Richard Zens, Franz Josef Och, Hermann Ney, EACL, 2003, pp. 387-394.
Minimum Error Rate Training in Statistical Machine Translation, Franz Josef Och, ACL, 2003, pp. 160-167.
Statistical Phrase-Based Translation, Philipp Koehn, Franz Josef Och, Daniel Marcu, HLT-NAACL, 2003.
Discriminative Training and Maximum Entropy Models for Statistical Machine Translation, Franz Josef Och, Hermann Ney, ACL, 2002, pp. 295-302.
Efficient Integration of Maximum Entropy Lexicon Models within the Training of Statistical Alignment Models, Ismael Garc, Franz Josef Och, Hermann Ney, Francisco Casacuberta, AMTA, 2002, pp. 54-63.
Improving Alignment Quality in Statistical Machine Translation Using Context-dependent Maximum Entropy Models, Ismael Garc, Franz Josef Och, Hermann Ney, Francisco Casacuberta, COLING, 2002.
Maximum Entropy and Gaussian Models for Image Object Recognition, Daniel Keysers, Franz Josef Och, Hermann Ney, DAGM-Symposium, 2002, pp. 498-506.
Phrase-Based Statistical Machine Translation, Richard Zens, Franz Josef Och, Hermann Ney, KI, 2002, pp. 18-32.
Refined Lexikon Models for Statistical Machine Translation Using a Maximum Entropy Approach, Ismael Garc, Franz Josef Och, Hermann Ney, Francisco Casacuberta, ACL, 2001, pp. 204-211.
A Comparison of Alignment Models for Statistical Machine Translation, Franz Josef Och, Hermann Ney, COLING, 2000, pp. 1086-1090.
Improved Statistical Alignment Models, Franz Josef Och, Hermann Ney, ACL, 2000.
The Statistical Translation Module in the Verbmobil System, Stephan Vogel, Franz Josef Och, Hermann Ney, KONVENS, 2000, pp. 291-293.
An Efficient Method for Determining Bilingual Word Classes, Franz Josef Och, EACL, 1999, pp. 71-76.
Improving Statistical Natural Language Translation with Categories and Rules, Franz Josef Och, Hans Weber, COLING-ACL, 1998, pp. 985-989.