ImportantMy FBK email address is no more valid! Use this instead: A.Bisazza [at] uva.nl
I've left Trento to start a new adventure. I may never express enough gratitude for being part of such a great research team. My colleagues and friends, I will miss you all very much!
I've successfully defended my thesis!! Thanks to all my colleagues for their support, and to my committee members for their stimulating comments and questions!
- Improving word reordering for SMT between distant languages
- Linguistic pre-processing for SMT involving morphologically rich languages such Arabic and Turkish
- How linguistic knowledge can improve statistical MT techniques
Automatic Speech Recognition for Arabic
- Diacritization of Arabic script
- Morphological pre-processing
Software & scripts
- Phrase table fillup & other combination techniques for translation model adaptation: combine-ptables
- Hybrid Language Models: map infrequent words to POS tags and train topic-generic models for language style adaptation (implementation).
- Turkish Morphological Segmentation (designed as pre-processing for SMT from Turkish to English): whole preprocessing workflow or segmentation rules only.
- Unitex for Turkish
- Local grammars for Turkish subordinate clause classification.
2009-2013 Phd in Statistical Machine Translation
FBK - Human Language Technologies & University of Trento, Italy
- PC member of IWSLT (2010), ACL, WMT and EMNLP (2012)
- Best student paper at IWSLT-11
- Co-responsible for systems competing at NIST-MT 2009, IWSLT 2009 to 2012
- Speech recognition for Arabic
- Advisor: Marcello Federico
- PhD thesis title: "Linguistically motivated reordering modeling for phrase-based statistical machine translation"
- PhD commitee: Philip Koehn, Alexander Fraser, Christof Monz
2012 -- Research Internship
Dublin City University, Ireland
- Selective dependency subtree pre-ordering for phrase-based SMT
2011 -- Research Internship
Microsoft Research, Redmond, WA
- Discriminative models for improved reordering in dependency-based SMT
2008 -- Research Internship
University of Trento - Dipartimento di Ingegneria e Scienza dell'Informazione, Trento, Italy
- Annotation of speech corpora for Spoken Language Understanding
Publications (see also my Google Scholar profile)
- A. Bisazza. Linguistically motivated reordering modeling for phrase-based statistical machine translation. University of Trento. April 2013.
- A. Bisazza, D. Pighin, M.Federico. Chunk-Lattices for Verb Reordering in Arabic-English SMT. In Machine Translation, Special Issue on MT for Arabic. Volume 26, Numbers 1-2. 2012.
- A. Bisazza, M. Federico. Modified Distortion Matrices for Phrase-Based Statistical Machine Translation. In Proc. of ACL, Jeju, Korea, 2012. [slides]
- A. Bisazza, M. Federico. Cutting the Long Tail: Hybrid Language Models for Translation Style Adaptation. In Proc. of EACL, Avignon, France, 2012. [poster]
- A. Bisazza, R. Gretter. Building a Turkish ASR system with minimal resources. In Proc. of LREC Workshop on Language Resources and Technologies for Turkic Languages, Istanbul, Turkey, 2012. [slides]
- A. Bisazza, N. Ruiz, and M. Federico. Fill-up versus Interpolation Methods for Phrase-based SMT Adaptation. In Proc. of the International Workshop on Spoken Language Translation, San Francisco, USA, 2011. Best Student Paper Award
- A. Bisazza and M. Federico, Chunk-Based Verb Reordering in VSO Sentences for Arabic-English Statistical Machine Translation. In Proceedings of the ACL 2010 Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR. Uppsala, Sweden, 2010. [slides]
- A. Bisazza, M. Federico. Morphological Pre-Processing for Turkish to English Statistical Machine Translation. In IWSLT 2009 - International Workshop on Spoken Language Translation, Tokyo, Japan, 2009.
- A. Bisazza. Designing a NooJ module for Turkish inflectional analysis: an example of highly productive morphology. In A. Ben Hamadou, S. Mesfar, M. Silberztein Eds "NooJ 2009 International Conference and Workshop." Sfax, Tunisia, 2010. [slides]
- A. Bisazza, M. Dinarelli, S. Quarteroni, S. Tonelli, A. Moschitti, G. Riccardi, Semantic Annotations for Conversational Speech: from Speech Transcriptions to Predicate Argument Structures, SLT 2008
- N Ruiz, A Bisazza, R Cattoni, M Federico. FBK's Machine Translation Systems at IWSLT 2012's TED Lectures. In Proc. of the International Workshop on Spoken Language Translation, San Francisco, USA, 2011.
- N. Ruiz, A. Bisazza, F. Brugnara, D. Falavigna, D. Giuliani, S. Jaber, R. Gretter, M. Federico. FBK@ IWSLT 2011. In Proc. of the International Workshop on Spoken Language Translation, San Francisco, USA, 2011.
- A. Bisazza, I. Klasinas, M. Cettolo, M. Federico. FBK @ IWSLT 2010. In Proc. of the International Workshop on Spoken Language Translation, Paris, France, 2010.
- Ch. Hardmeier, A. Bisazza and M. Federico, FBK at WMT 2010: Word Lattices for Morphological Reduction and Chunk-Based Reordering. In Proceedings of the ACL 2010 Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR. Uppsala, Sweden, 2010.
- N. Bertoldi, A. Bisazza, M. Cettolo, M. Federico and G. Sanchis-Trilles. FBK @ IWSLT 2009. In Proc. of the International Workshop on Spoken Language Translation, Tokyo, Japan, 2009.
- A. Bisazza, La représentation du turc en Unitex (Master Thesis in French), Supervisor: Pierre Zweigenbaum, Paris, 24 October 2008.
- Pre-ordering Dependency Subtrees for Phrase-Based SMT, Dublin City University, November 2012.
- Recent SMT advances at FBK, Microsoft Research, Redmond, May 2011.