Wolfgang Macherey joined Google in 2006 as a research scientist, where he works in the machine translation group with Franz Josef Och. He has been working on natural language processing since 1996.
Wolfgang worked as a Research Assistant at RWTH Aachen University from 1999 to 2005. His main research interests are in statistical machine translation and automatic speech recognition with the focus on discriminative training methods, natural language processing, statistical pattern recognition, and machine learning.
He received a PhD in Computer Science from RWTH Aachen University, Germany, in 2010 and his Diploma Degree in Computer Science from RWTH Aachen University in 1999 with a major in statistical pattern recognition and a minor in physical chemistry and thermodynamics.
“Expected Sequence Similarity Maximization”, Cyril Allauzen, Shankar Kumar, Wolfgang Macherey, Mehryar Mohri, Michael Riley, NAACL HLT, 2010.
[aclweb.org] [pdf] [search]
“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.
[pdf] [search]
“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.
[abstract] [aclweb.org] [pdf] [search]
“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.
[abstract] [aclweb.org] [pdf] [search]
“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.
[abstract] [aclweb.org] [pdf] [search]
“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.
[abstract] [aclweb.org] [pdf] [search]
“Discriminative Training and Acoustic Modeling for Automatic Speech Recognition”, Wolfgang Macherey, 2010, pp. 218.
[darwin.bth.rwth-aachen.de] [search]
“Investigations on Error Minimizing Training Criteria for Discriminative Training in Automatic Speech Recognition”, Wolfgang Macherey, Lars Haferkamp, Ralf Schlueter, Hermann Ney, Europ. Conf. on Speech Communication and Technology, 2005, pp. 2133-2136.
[www-i6.informatik.rwth-aachen.de] [search]
“Minimum Exact Word Error Training”, Georg Heigold, Wolfgang Macherey, Ralf Schlueter, Hermann Ney, Automatic Speech Recognition and Understanding, 2005, pp. 186-190.
[www-i6.informatik.rwth-aachen.de] [search]
“Adaptation in Statistical Pattern Recognition Using Tangent Vectors”, Daniel Keysers, Wolfgang Macherey, Hermann Ney, Joerg Dahmen, IEEE Trans. Pattern Anal. Mach. Intell., vol. 26 (2004), pp. 269-274.
[www-i6.informatik.rwth-aachen.de] [search]
“Discriminative Training with Tied Covariance Matrices”, Wolfgang Macherey, Ralf Schlueter, Hermann Ney, 8th Int. Conf. on Spoken Language Processing (ICSLP), 2004, pp. 681-684.
[www-i6.informatik.rwth-aachen.de] [search]
“A Comparative Study on Maximum Entropy and Discriminative Training for Acoustic Modeling in Automatic Speech Recognition”, Wolfgang Macherey, Hermann Ney, Proc. European Conference on Speech Communication and Technology, 2003, pp. 493-496.
[isca-speech.org] [search]
“Probabilistic Aspects in Spoken Document Retrieval”, Wolfgang Macherey, Joerg Viechtbauer, Hermann Ney, EURASIP Journal on Applied Signal Processing (2003), pp. 115-127.
[www-i6.informatik.rwth-aachen.de] [search]
“Probabilistic Retrieval Based On Document Representations”, Wolfgang Macherey, Joerg Viechtbauer, Hermann Ney, Int. Conf. on Spoken Language Processing, 2002, pp. 1481-1484.
[citeseerx.ist.psu.edu] [search]
“Towards Automatic Corpus Preparation for a German Broadcast News Transcription System”, Wolfgang Macherey, Hermann Ney, Int. Conf. on Spoken Language Processing, 2002, pp. 733-736.
[ieeexplore.ieee.org] [search]
“Comparison of Discriminative Training Criteria and Optimization Methods for Speech Recognition”, Ralf Schlueter, Wolfgang Macherey, Boris Mueller, Hermann Ney, Speech Communication, vol. 34 (2001), pp. 287-310.
[www-i6.informatik.rwth-aachen.de] [search]
“Improving Automatic Speech Recognition Using Tangent Distance”, Wolfgang Macherey, Daniel Keysers, Joerg Dahmen, Hermann Ney, European Conference on Speech Communication and Technology, 2001.
[www-i6.informatik.rwth-aachen.de] [search]
“Learning of Variability for Invariant Statistical Pattern Recognition”, Daniel Keysers, Wolfgang Macherey, Joerg Dahmen, Hermann Ney, European Conference on Machine Learning (ECML), 2001, pp. 263-275.
[www-i6.informatik.rwth-aachen.de] [search]
“A Combined Maximum Mutual Information and Maximum Likelihood Approach for Mixture Density Splitting”, Ralf Schlueter, Wolfgang Macherey, Boris Mueller, Hermann Ney, Europ. Conf. on Speech Communication and Technology, 1999, pp. 1715-1718.
[www-i6.informatik.rwth-aachen.de] [search]
“Comparison of Discriminative Training Criteria”, Ralf Schlueter, Wolfgang Macherey, Int. Conf. on Acoustics, Speech, and Signal Processing, 1998, pp. 493-496.
[www-i6.informatik.rwth-aachen.de] [search]
“Implementierung und Vergleich diskriminativer Verfahren fuer Spracherkennung bei kleinem Vokabular”, Wolfgang Macherey, Diploma Thesis, 1998, pp. 123.
[search]
“Comparison of Optimization Methods for Discriminative Training Criteria”, Ralf Schlueter, Wolfgang Macherey, Stephan Kanthak, Hermann Ney, Lutz Welling, Europ. Conf. on Speech Communication and Technology, 1997, pp. 15-18.
[www-i6.informatik.rwth-aachen.de] [search]