Jump to Content
Klaus Macherey

Klaus Macherey

Klaus Macherey joined Google in 2006 as a research scientist, where he works in the machine translation group. He has been working on natural language processing since 1996.

Klaus was 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 natural language understanding and spoken dialogue systems, natural language processing, statistical pattern recognition, and machine learning.

He received a PhD in Computer Science from RWTH Aachen University, Germany, in 2009 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.

Authored Publications
Google Publications
Other Publications
Sort By
  • Title
  • Title, desc
  • Year
  • Year, desc
    Preview abstract In this paper we share findings from our effort towards building practical machine translation (MT) systems capable of translating across over one thousand languages. We describe results across three research domains: (i) Building clean, web-mined datasets by leveraging semi-supervised pre-training for language-id and developing data-driven filtering techniques; (ii) Leveraging massively multilingual MT models trained with supervised parallel data for over $100$ languages and small monolingual datasets for over $1000$ languages to enable translation for several previously under-studied languages; and (iii) Studying the limitations of evaluation metrics for long tail languages and conducting qualitative analysis of the outputs from our MT models. We hope that our work provides useful insights to practitioners working towards building MT systems for long tail languages, and highlights research directions that can complement the weaknesses of massively multilingual pre-trained models in data-sparse settings. View details
    Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
    Mike Schuster
    Mohammad Norouzi
    Maxim Krikun
    Qin Gao
    Apurva Shah
    Xiaobing Liu
    Łukasz Kaiser
    Stephan Gouws
    Taku Kudo
    Keith Stevens
    George Kurian
    Nishant Patil
    Wei Wang
    Jason Smith
    Alex Rudnick
    Macduff Hughes
    CoRR, vol. abs/1609.08144 (2016)
    Preview abstract Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, with the potential to overcome many of the weaknesses of conventional phrase-based translation systems. Unfortunately, NMT systems are known to be computationally expensive both in training and in translation inference. Also, most NMT systems have difficulty with rare words. These issues have hindered NMT's use in practical deployments and services, where both accuracy and speed are essential. In this work, we present GNMT, Google's Neural Machine Translation system, which attempts to address many of these issues. Our model consists of a deep LSTM network with 8 encoder and 8 decoder layers using attention and residual connections. To improve parallelism and therefore decrease training time, our attention mechanism connects the bottom layer of the decoder to the top layer of the encoder. To accelerate the final translation speed, we employ low-precision arithmetic during inference computations. To improve handling of rare words, we divide words into a limited set of common sub-word units ("wordpieces") for both input and output. This method provides a good balance between the flexibility of "character"-delimited models and the efficiency of "word"-delimited models, naturally handles translation of rare words, and ultimately improves the overall accuracy of the system. Our beam search technique employs a length-normalization procedure and uses a coverage penalty, which encourages generation of an output sentence that is most likely to cover all the words in the source sentence. On the WMT'14 English-to-French and English-to-German benchmarks, GNMT achieves competitive results to state-of-the-art. Using a human side-by-side evaluation on a set of isolated simple sentences, it reduces translation errors by an average of 60% compared to Google's phrase-based production system. View details
    Model-Based Aligner Combination Using Dual Decomposition
    John DeNero
    Proceedings of the Association for Computational Linguistics (ACL), 2011
    Preview abstract Unsupervised word alignment is most often modeled as a Markov process that generates a sentence f conditioned on its translation e. A similar model generating e from f will make different alignment predictions. Statistical machine translation systems combine the predictions of two directional models, typically using heuristic combination procedures like grow-diag-final. This paper presents a graphical model that embeds two directional aligners into a single model. Inference can be performed via dual decomposition, which reuses the efficient inference algorithms of the directional models. Our bidirectional model enforces a one-to-one phrase constraint while accounting for the uncertainty in the underlying directional models. The resulting alignments improve upon baseline combination heuristics in word-level and phrase-level evaluations. View details
    Preview abstract Translating compounds is an important problem in machine translation. Since many compounds have not been observed during training, they pose a challenge for translation systems. Previous decompounding methods have often been restricted to a small set of languages as they cannot deal with more complex compound forming processes. We present a novel and unsupervised method to learn the compound parts and morphological operations needed to split compounds into their compound parts. The method uses a bilingual corpus to learn the morphological operations required to split a compound into its parts. Furthermore, monolingual corpora are used to learn and filter the set of compound part candidates. We evaluate our method within a machine translation task and show significant improvements for various languages to show the versatility of the approach. View details
    Feature Functions for Tree-Based Dialogue Course Management
    Hermann Ney
    SPOKEN MULTIMODAL HUMAN-COMPUTER DIALOGUE IN MOBILE ENVIRONMENTS, Springer (2005)
    Features for Tree-Based Dialogue Course Management
    Hermann Ney
    Proc. European Conference on Speech Communication and Technology (2003), pp. 601-604
    Confidence Measures for Statistical Machine Translation.
    Nicola Ueffing
    Hermann Ney
    Machine Translation Summit IX, New Orleans, LO (2003), pp. 394-401
    Multi-Level Error Handling for Tree-Based Dialogue Course Management
    Oliver Bender
    Hermann Ney
    ISCA Tutorial and Research Workshop on Error Handling in Spoken Dialogue Systems, Chateau-d'Oex-Vaud, Switzerland (2003), pp. 123-128
    Comparison of Alignment Templates and Maximum Entropy Models for Natural Language Understanding
    Oliver Bender
    Franz Josef Och
    Hermann Ney
    EACL (2003), pp. 11-18
    Systemprogrammierung
    Otto Spaniol
    Mesut Günes
    Ralf Wienzek
    St. Augustine, Aachen (2002)
    Scoring Criteria for Tree Based Dialogue Course Management
    Hermann Ney
    ISCA Tutorial and Research Workshop Multi-Modal Dialogue in Mobile Environments (2002)
    Natural Language Understanding Using Statistical Machine Translation
    Franz Och
    Hermann Ney
    Proceedings of EUROSPEECH-2001, pp. 2205-2208
    A Comparison of Word Graph and N-Best List Based Confidence Measures
    Frank Wessel
    Hermann Ney
    Proc. Sixth European Conference on Speech Communication and Technology (1999), pp. 315-318
    Using Word Probabilities as Confidence Measures
    F. Wessel
    Ralf Schlüter
    Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (1998), pp. 225-228