Welcome to the homepage of Saša Hasan, currently PhD student at the
Human Language Technology and Pattern Recognition group, RWTH Aachen University, Germany.

• Human Language Technology, in particular Automatic Speech Recognition and Statistical Machine Translation
• Pattern Recognition
• Image Processing and Recognition

You might have a look at the full list of publications of the group.

Saša Hasan received his diploma degree in Computer Science with major subject Computational Linguistics from the University of Koblenz-Landau in 2003. His thesis was on ambiguous keyboards and their usage within a syntactically enhanced disambiguation framework based on supertagging and lightweight dependency analysis. He held a DAAD scholarship from 1999 to 2000 and studied at the Institute for Artificial Intelligence at the University of Georgia in Athens. In 2007, he joined Google's Machine Translation Group for a software engineering internship. He was a PhD student and research assistant at RWTH Aachen University from 2003 to 2009. His research focused on statistical machine translation, in particular n-best reranking and extended lexicon modeling. Until recently, he worked at Nuance Communications as speech scientist in the Embedded R&D group focusing on music retrieval for the automotive market. In October 2011, he joined SDL Language Weaver as research scientist.

2011

• S. Hasan, S. Mansour, H. Ney: A comparison of segmentation methods and extended lexicon models for Arabic statistical machine translation. In Machine Translation, Springer Netherlands, September 2011.

2010

• K. Harbusch, J. Bäcker, S. Hasan: Applications of HMM-Based Supertagging. Book chapter in Supertagging - Using Complex Lexical Descriptions in Natural Language Processing, Eds. Srinivas Bangalore and Aravind Joshi, MIT Press, March 2010.

2009

• A. Mauser, S. Hasan and H. Ney. Extending Statistical Machine Translation with Discriminative and Trigger-Based Lexicon Models. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2009), pp. 210-218, Singapore, August 2009.

• S. Hasan and H. Ney. Comparison of Extended Lexicon Models in Search and Rescoring for SMT. In Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers (NAACL HLT 2009), pp. 17-20, Boulder, Colorado, June 2009.

• M. Akbacak, H. Franco, M. Frandsen, S. Hasan, H. Jameel, A. Kathol, S. Khadivi, X. Lei, A. Mandal, S. Mansour, K. Precoda, C. Richey, D. Vergyri, W. Wang, M. Yang, and J. Zheng. Recent Advances in SRI's IRAQCOMM™ Iraqi Arabic-English Speech-to-Speech Translation System. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Taipei, Taiwan, April 2009.
• T. Deselaers, S. Hasan, O. Bender, and H. Ney. A Deep Learning Approach to Machine Transliteration. In Proceedings of the EACL 2009 Workshop on Statistical Machine Translation (WMT09), Athens, Greece, March 2009.

2008

• S. Hasan, J. Ganitkevitch, H. Ney, and J. Andrés-Ferrer: Triplet Lexicon Models for Statistical Machine Translation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2008), pp. 372-381, Honolulu, Hawaii, October 2008.

• S. Hasan and H. Ney: A Multi-Genre SMT System for Arabic to French. In Proceedings of LREC 2008 (6th International Conference on Language Resources and Evaluation), Marrakech, Morocco, May 2008.

• A. Mauser, S. Hasan, and H. Ney: Automatic Evaluation Measures for Statistical Machine Translation System Optimization. In Proceedings of LREC 2008 (6th International Conference on Language Resources and Evaluation), Marrakech, Morocco, May 2008.

2007

• O. Bender, E. Matusov, S. Hahn, S. Hasan, S. Khadivi, and H. Ney: The RWTH Arabic-to-English Spoken Language Translation System. In Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2007), pp. 396-401, Kyoto, Japan, December 2007.

• R. Zens, S. Hasan, and H. Ney: A Systematic Comparison of Training Criteria for Statistical Machine Translation. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2007), pp. 524-532, Prague, Czech Republic, June 2007.

• S. Hasan, R. Zens, and H. Ney: Are Very Large N-best Lists Useful for SMT? Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics (NAACL HLT 2007), Companion Volume: Short Papers, pp. 57-60, Rochester, NY, April 2007.

2006

• A. Mauser, R. Zens, E. Matusov, S. Hasan, and H. Ney: The RWTH Statistical Machine Translation System for the IWSLT 2006 Evaluation. In Proceedings of the International Workshop on Spoken Language Translation, pp. 103-110, Kyoto, Japan, November 2006. (best paper award)

• E. Matusov, R. Zens, D. Vilar, A. Mauser, M. Popović, S. Hasan, and H. Ney: The RWTH Machine Translation System. In Proceedings of the TC-STAR Workshop on Speech-to-Speech Translation, pp. 31-36, Barcelona, Spain, June 2006.

• S. Hasan, S. Khadivi, R. Zens, and H. Ney: A Flexible Architecture for CAT Applications. In Proceedings of EAMT 2006 (11th Annual Conference of the European Association for Machine Translation), pp. 81-88, Oslo, Norway, June 2006.

• S. Hasan, A. El Isbihani, and H. Ney: Creating a Large-Scale Arabic to French Statistical Machine Translation System. In Proceedings of LREC 2006 (5th International Conference on Language Resources and Evaluation), pp. 855-858, Genoa, Italy, May 2006.

• S. Hasan, O. Bender, and H. Ney: Reranking Translation Hypotheses Using Structural Properties. In Proceedings of the EACL'06 Workshop on Learning Structured Information in Natural Language Applications, pp. 41-48, Trento, Italy, April 2006.

2005

• R. Zens, O. Bender, S. Hasan, S. Khadivi, E. Matusov, J. Xu, Y. Zhang, and H. Ney: The RWTH Phrase-based Statistical Machine Translation System. In Proceedings of the International Workshop on Spoken Language Translation (IWSLT 2005), pp. 155-162, Pittsburgh, PA, October 2005.

• D. Vilar, E. Matusov, S. Hasan, R. Zens, and H. Ney: Statistical Machine Translation of European Parliamentary Speeches. In Proceedings of the MT SUMMIT X, pp. 259-266, Phuket, Thailand, September 2005.

• O. Bender, S. Hasan, D. Vilar, R. Zens, and H. Ney: Comparison of Generation Strategies for Interactive Machine Translation. In Proceedings of EAMT 2005 (10th Annual Conference of the European Association for Machine Translation), pp. 33-40, Budapest, Hungary, May 2005.

• S. Hasan and H. Ney: Clustered Language Models based on Regular Expressions for Statistical Machine Translation. In Proceedings of EAMT 2005 (10th Annual Conference of the European Association for Machine Translation), pp. 119-125, Budapest, Hungary, May 2005.

2004

• S. Hasan and K. Harbusch: N-Best Hidden Markov Model Supertagging to Improve Typing on an Ambiguous Keyboard. Proceedings of the 7th International Workshop on Tree Adjoining Grammars and Related Formalisms (TAG+7), Vancouver, Canada, May 2004.

2003

• K. Harbusch, S. Hasan, H. Hoffmann, M. Kühn, B. Schüler: Topic- and Author-Specific Suggestion Lists for Typing with Ambiguous Keyboards. Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2003), Borovets, Bulgaria, September 2003.

• S. Hasan: N-Best Hidden Markov Model Supertagging for Typing with Ambiguous Keyboards. Diploma Thesis, Computer Science Department, University of Koblenz-Landau, Koblenz, Germany, July 2003.

• K. Harbusch, S. Hasan, H. Hoffmann, M. Kühn, B. Schüler: Domain-Specific Disambiguation for Typing with Ambiguous Keyboards. Proceedings of the Workshop on Language Modeling for Text Entry Methods at the 10th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2003), Budapest, Hungary, April 2003.

2008

• Diploma thesis supervisor: Lexical Triggers for Statistical Machine Translation by Juri Ganitkevitch (Oct 08)
• Lab course Speech- and Image Processing (winter semester 08/09)
• Seminar Selected Topics in Pattern Recognition (summer semester 08)
• Lab course Pattern Classification and Image Recognition (summer semester 08)

2007

• Lab course Speech- and Image Processing (winter semester 07/08)
• Lab course Pattern Classification and Image Recognition (summer semester 07)

2006

• Lab course Speech- and Image Processing (winter semester 06/07)
• Lab course Pattern Classification and Image Recognition (summer semester 06)

2005

• Lab course Speech- and Image Processing (winter semester 05/06)
• Master thesis supervisor: Language Modeling based on Latent Semantic Analysis by Stefan Savev (Aug 05)
• Lab course Pattern Classification and Image Recognition (summer semester 05)

2004

• Seminar Human Language Technology (summer semester 04)

• Improving SMT by Using Multiple Translation Hypotheses: talk at the TC-STAR OpenLab on Speech Translation, Trento, Italy, March 30, 2006.
• Reranking Translation Hypotheses Using Structural Properties: talk at the EACL 2006 Workshop on Learning Structured Information in Natural Language Applications, Trento, Italy, April 3, 2006.
• Creating a Large-Scale Arabic to French SMT System: talk at the Fifth International Conference on Language Resources and Evaluation (LREC), Genoa, Italy, May 25, 2006.
• A Flexible Architecture for CAT Applications: talk at the 11th Annual Conference of the European Association for Machine Translation (EAMT), Oslo, Norway, June 20, 2006.
• Translation from Arabic to French: talk at the Séminaire DGA/CEP, «Traitement du langage: état de l'art, projets et perspectives», Centre d'expertise parisien (CEP), Arcueil, France, June 27, 2006.
• The RWTH Statistical Machine Translation System: talk at the NIST MT Evaluation Workshop 2006, Washington D.C., September 6, 2006.
• Are Very Large N-Best Lists Useful for SMT?: talk at the Human Language Technologies Conference (NAACL HLT 2007), Rochester, New York, April 24, 2007.
• Recent Progress in Machine Translation: talk at the Séminaire DGA/DET/CEP, «Traitement de la parole, du langage et des documents multimédias», Centre d'expertise parisien (CEP), Arcueil, France, June 21, 2007.
• A Multi-Genre SMT system for Arabic to French: talk at the Sixth International Conference on Language Resources and Evaluation (LREC), Marrakech, Morocco, May 29, 2008 and at the Séminaire DGA/DET, «Traitement de la parole, du langage et des documents multimédias», ENSTA, Paris, France, June 25, 2008.
• The TRAMES System: talk at the Quaero WP 4 & 5 meeting, Karlsruhe, Germany, July 1, 2008.
• Triplet Lexicon Models for Statistical Machine Translation: talk at SRI International, Menlo Park, CA, October 15, 2008.
• Extended Lexicon Models for Statistical Machine Translation: talk at the Quaero CTC Workshop, Aachen, Germany, March 11, 2009.
• A Deep Learning Approach to Machine Transliteration: talk at the EACL 2009 Workshop on Statistical Machine Translation, Athens, Greece, March 31, 2009.
• Comparison of Extended Lexicon Models in Search and Rescoring for SMT: short talk at NAACL HLT 2009, Boulder, CO, June 1, 2009.
• Statistical Machine Translation using a Triplet Word Lexicon: talk at the Séminaire DGA, «Traitement de la parole, du langage et des documents multimédias», ENSTA, Paris, France, June 30, 2009.

For your information: my first name (Saša) is pronounced Sasha, I'm male (yes, there were a few cases of people addressing me as "Mrs." :) and in e-mails, you will find my name being written as Sasa. This oddity is obfuscating most people's minds, so this small notice should settle the confusion. If you're curious about the origin of the name: it's the Russian short form of Alexander. However, I'm not Russian but Croatian , although my last name is not typical for Croatia. Heck, I don't know, it's kinda weird. :)

Additional hints (I am really happy if people get the spelling correct, especially in citations):

• LaTeX: Sa\v{s}a (please check your BibTeX entries ;)
• HTML: Saša

Short CV

Last modified: Thu Sep 8 18:34:13 CEST 2011 [Disclaimer]