Personal

Welcome to the homepage of Andreas Guta.

Currently I am PhD student within the Human Language Technology and Pattern Recognition Group at the Chair of Computer Science 6 of the RWTH Aachen University.

The main research topics of the chair are

Pattern Recognition
Automatic Speech Recognition
Statistical Machine Translation
Image Processing

I am part of the machine translation group. The focus of my work is on training and decoding for extended translation and reordering models.

You can find me in room 6125b of our department, call me at +49 241 80 21632 or write an e-mail to <surname>@i6.informatik.rwth-aachen.de

Short CV

04/2017 - today	Machine Learning Scientist at AppTek
03/2012 - today	Research Assistant at the Lehrstuhl für Informatik 6, RWTH Aachen University
06/2016 - 09/2016	Internship at Google Inc., Google Play Apps, Mountain View, CA, USA
10/2003 - 02/2012	Computer Science at the RWTH Aachen (Diplom)

Teaching

Course Work

Statistical Methods in Natural Language Processing, Winter 2013/14, with Christoph Schmidt.
Statistical Methods in Natural Language Processing, Summer 2015.
Statistical Methods in Natural Language Processing, Summer 2016, with Weiyue Wang.

Seminar Supervision

Selected Topics in Human Language Technology and Pattern Recognition, Winter 2014/15, Topics: "IBM Translation Models", "N-gram-based Machine Translation", "Operation Sequence Model".
Selected Topics in Human Language Technology and Pattern Recognition, Winter 2015/16, Topics: "N-gram-based Machine Translation", "Operation Sequence Model".

Lab Courses

Undergrad software lab Machine Translation, Summer 2015, with Jan-Thorsten Peter.
Undergrad software lab Machine Translation, Summer 2016, with Jan-Thorsten Peter and Julian Schamper.
Undergrad software lab Machine Translation, Summer 2016, with Jan-Thorsten Peter and Jan Rosendahl.

Supervision

Master thesis of Yunsu Kim, "Phrase-table Smoothing with Word Classes", 2015.
Bachelor thesis of Miguel Graça, "Word-based Decoding with Joint Translation and Reordering Models", 2016.
Master thesis of Patrick Wilken, "Training of Extended Count-Based Models for Statistical Machine Translation", 2018.

Publications

2020

P. Bahar, P. Wilken, T. Alkhouli, A. Guta, P. Golik, E. Matusov, and C. Herold. Start-Before-End and End-to-End: Neural Speech Translation by AppTek and RWTH Aachen University. In The 17th International Workshop on Spoken Language Translation (IWSLT), Seattle, WA, United States, July 2020.

2017

J. Peter, A. Guta, T. Alkhouli, P. Bahar, J. Rosendahl, N. Rossenbach, M. Graça, and Ney Hermann. The RWTH Aachen University English-German and German-English Machine Translation System for WMT 2017. In EMNLP 2017 Second Conference on Machine Translation (WMT 2017), Copenhagen, Denmark, September 2017.

2016

J. Peter, A. Guta, N. Rossenbach, M. Graça, and H. Ney. The RWTH Aachen Machine Translation System for IWSLT 2016. In International Workshop on Spoken Language Translation (IWSLT), Seattle, USA, December 2016.
J. Peter, T. Alkhouli, A. Guta, and Ney Hermann. The RWTH Aachen University English-Romanian Machine Translation System for WMT 2016. In ACL 2016 First Conference on Machine Translation (WMT 2016), pages 356–361, Berlin, Germany, August 2016.
T. Alkhouli, G. Bretschner, J. Peter, M. Hethnawi, A. Guta, and H. Ney. Alignment-Based Neural Machine Translation. In ACL 2016 First Conference on Machine Translation (WMT 2016), pages 54-65, Berlin, Germany, August 2016.
Y. Kim, A. Guta, J. Wuebker, and H. Ney. A Comparative Study on Vocabulary Reduction for Phrase Table Smoothing. In ACL 2016 First Conference on Machine Translation (WMT 2016), pages 110-117, Berlin, Germany, August 2016. [slides].

2015

J. Peter, F. Toutounchi, S. Peitz, P. Bahar, A. Guta, and H. Ney. The RWTH Aachen German to English MT System for IWSLT 2015. In International Workshop on Spoken Language Translation (IWSLT), pages 15-22, Da Nang, Vietnam, December 2015.
A. Guta, J. Wuebker, M. Graça, Y. Kim, and H. Ney. Extended Translation Models in Phrase-based Decoding. In EMNLP 2015 Tenth Workshop on Statistical Machine Translation (WMT 2015), pages 282-293, Lisbon, Portugal, September 2015.
A. Guta, T. Alkhouli, J. Peter, J. Wuebker, and H. Ney. A Comparison between Count and Neural Network Models Based on Joint Translation and Reordering Sequences. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP 2015), pages 1401-1411, Lisbon, Portugal, September 2015.

2014

J. Wuebker, S. Peitz, A. Guta, and H. Ney. The RWTH Aachen Machine Translation Systems for IWSLT 2014. In International Workshop on Spoken Language Translation (IWSLT), pages 150-154, Lake Tahoe, CA, USA, December 2014.
T. Alkhouli, A. Guta, and H. Ney. Vector Space Models for Phrase-based Machine Translation. In EMNLP 2014 Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation (SSST-8), pages 1-10, Doha, Qatar, October 2014.

2012

P. Lehnen, S. Hahn, A. Guta, and H. Ney. Hidden Conditional Random Fields with M-to-N Alignments for Grapheme-to-Phoneme Conversion. In Interspeech, pages 2554-2557, Portland, OR, USA, September 2012.

2011

P. Lehnen, S. Hahn, A. Guta, and H. Ney. Incorporating Alignments into Conditional Random Fields for Grapheme to Phoneme Conversion. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 4916-4919, Prague, Czech Republic, May 2011.
A. Guta. Grapheme to Phoneme Conversion Using CRFs with Integrated Alignments. Master Thesis, Computer Science Department, RWTH Aachen University, Aachen, May 2011.

Full list of publications of the chair.