Short bio
Nicola Bertoldi was born in Trento, Italy in 1976. He received his
degree in Mathematics from the University of Trento, Italy with honours
in 2000. He received Ph.D. degree from the the University of Trento,
Italy in 2005.
Since 2000 he has been working as researcher in the FBK - Fondazione Bruno Kessler,
(former ITC-irst
- Center for Scientific and Technological Research)
joining the HERMES research line (former MUNST project) in the Interactive Sensory Systems (SSI).
His research
interests include Statistical Machine Translation, Spoken Language
Translation, Language Modelling, Text Classification, Information
Retrieval, Information Extraction.
From March 2005 to March 2007 he was
involved in the EU Integrated Project
TC-STAR
focusing on Statistical Machine Translation and Spoken
Language Translation.
He participated as senior researcher in the 2006 Workshop "Open Source Toolkit for Statistical Machine Translation" organized by the Center for
Language and Speech Processing (JHU) collaborating in the development of an open source MT system for text and speech.
He served in the Program Committees of the International Workshops on Spoken Language Translation
(IWSLT 2006 and IWSLT 2007).
Past Activities |
Apr. 05 - Mar. 07
|
Contract researcher for the EU Integrated Project TC-STAR
within the HERMES research line (SSI, ITC-irst).
Research field: Machine Translation,
Spoken Language Translation, Translation through Confusion Network. |
Jul. 06 - Aug. 06
|
Senior Researcher at 2006 JHU-CLSP Summer Workshop "Open Source Toolkit for Statistical Machine Translation".
Granted by JHU. |
Nov. 01 - Nov. 04
|
Contract researcher for the WebFAQ Project funded by the local government
within the HERMES research line (MUNST until 2003) (SSI, ITC-irst).
Research field: Machine Translation,
Language Modelling, Information Retrieval, Information Extraction. |
| May 00 - Oct. 01 |
Research Assistant for EU Project CORETEX within the MUNST research line (SSI,
ITC-irst).
Research field: Language Modelling,
Information Retrieval, Text Classification, Part-of Speech Tagging. |
Teaching |
| Nov. 04 - Feb. 05 |
Teaching Assistant, "Computer Science 1",
Faculty of Telecommunication Engineering, U. Trento, Italy
Subject: C/C++ programming language, data structure, algorithms |
| Nov. 04 - Feb. 05 |
Tutor for students of the Faculty of Computer Science, U. Trento, Italy
|
| Sep. 01 - Feb. 02 |
Teaching Assistant, "Computer Science 1",
Faculty of Mathematics, U. Trento, Italy
Subject: C/C++ programming language, data structure, algorithms |
Education |
|
| February 2005 |
Ph.D. degree in Mathematics
Department of Mathematics, U. Trento, Italy
Dissertation: "Statistical Models and Search Algorithms for Machine Translation"
(Advisors: Prof. Roberto Battiti, and Dr. Marcello Federico) |
| March 2000 |
Laurea degree with honours in Mathematics
Faculty of Mathematics, University of Trento, Italy
Dissertation: "Analysis and
implementation of Statistical Models for POS tagging" (in Italian)
(Advisors: Prof. Luciano Tubaro, and Dr. Marcello Federico) |
Publication
Journal Papers
- Matusov, Leusch, Banchs, Bertoldi, Déchelotte, Federico, Kolss, Le,
Mariño, Paulik, Roukos, Schwenk"System Combination for Machine Translatio
of Spoken and Written Language". IEEE Transactions on Audio, Speech
and Language Processing. Accepted for publication.
- Federico and Bertoldi,
"A word-to-phrase statistical translation model". ACM Transactions on
Speech and Language Processing (TSLP). 2(2): pp. 1-24. December, 2005.
- Federico and
Bertoldi, "Broadcast News LM Adaptation over Time", Computer Speech and
Language. 18(4): pp. 417-435. October, 2004.
- Bertoldi and
Federico, "Statistical Model for Monolingual and Bilingual Information
Retrieval", Information Retrieval, 7(1-2): pp. 53-72. January, 2004.
- Bertoldi,
Brugnara, Cettolo, Federico, Giuliani, "Cross-Task Portability of a
Broadcast News Speech Recognition System". Speech Communication.
38(3-4): pp. 335-347. 2002.
Conferences Papers
- Bertoldi, Cettolo, Cattoni, Federico, "FBK @ IWSLT 2007". In Proc. International Workshop on Spoken Language Translation Evaluation Campaign on Spoken Language Translation (IWSLT). October, 2007. Trento, Italy.
- Cattoni, Bertoldi, Federico. "Punctuating Confusion Networks for Speech Translation". Proc. of InterSpeech. August, 2007, Antwerp, Belgium.
- Falavigna, Bertoldi, Brugnara, Cattoni, Cettolo, Chen, Federico, Giuliani, Gretter, Gupta, Seppi, " The IRST English-Spanish Translation System for European Parliament Speeches". In Proc. of InterSpeech. August, 2007, Antwerp, Belgium.
- Bertoldi, Zens, Federico. "Speech Translation by Confusion Network Decoding". In Proc. of the ICASSP. April, 2007, Honolulu, Hawaii, USA.
- Shen, Zens, Bertoldi, Federico, "The JHU Workshop 2006 IWSLT System". In International Workshop on Spoken Language Translation Evaluation Campaign on Spoken Language Translation (IWSLT). November, 2006. Kyoto, Japan.
- Chen, Cattoni, Bertoldi, Cettolo, Federico, "The ITC-irst SMT System for IWSLT-2006". In International Workshop on Spoken Language Translation Evaluation Campaign on Spoken Language Translation (IWSLT). November, 2006. Kyoto, Japan.
- Bertoldi, Cattoni, Cettolo, Chen, Federico.
"ITC-irst at the 2006 TC-STAR SLT Evaluation Campaign". In
Proc. of the TC-STAR Workshop on Speech-to-Speech Translation. pp. 18-24. June, 2006. Barcelona,
Spain.
-
Cattoni, Bertoldi, Cettolo, Chen, Federico. "Web-based Demonstrator of a Multi-lingual Phrase-based
Translation System". In Proc. of the 11th Conference of EACL, Posters and Demonstrations. pp. 91-94.
April, 2006. Trento, Italy.
- Federico, Bertoldi. "How Many Bits Are Needed To Store Probabilities for Phrase-Based Translation?". In
Proc. on the ACL Workshop on Statistical Machine Translation. pp. 94-101. June, 2006. New York City.
- Cattoni, Bertoldi, Cettolo, Chen, Federico. "A Web-based Interface to a Multi-lingual Phrase-based
Translation System". In Systems Demonstrations of the ECAI 2006. August, 2006. Riva del Garda, Italy.
- Bertoldi and Federico, "A New Decoder
for Spoken Language Translation based on Confusion Networks". In Proc.
of the IEEE Automatic Speech Recognition and Understanding Workshop.
December, 2005. Cancun, Mexico.
- Cettolo,
Federico, Bertoldi, Cattoni, and Chen "A Look Inside the ITC-irst SMT
System". In Proc. of the 10th Machine Translation Summit. pp. 451-457.
September, 2005. Phuket, Thailand.
- Chen,
Cattoni, Bertoldi, Cettolo, Federico, "The ITC-irst SMT System for
IWSLT 2005". In Proc. of the International Workshop on Spoken Language
Translation - IWSLT. pp. 98-104. October, 2005. Pittsburgh, USA
- Bertoldi,
Cattoni, Cettolo, Federico, "The ITC-irst Statistical Machine
Translation System for IWSLT-2004". In Proc. of the International
Workshop on Spoken Language Translation (IWSLT). pp. 51-58. September,
2004. Kyoto, Japan.
- Federico,
Bertoldi, Levow, Jones, "CLEF 2004 Cross-Language Spoken Document
Retrieval Track". In Working Notes for the CLEF 2004 Workshop.
September, 2004. Bath, UK.
- Bertoldi,
Federico, "ITC-irst at CLEF 2003: Cross-Language Spoken Document
Retrieval". In Comparative Evaluation of Multilingual Information
Access Systems: 4th Workshop of the Cross-Language Evaluation Forum,
CLEF 2003, Trondheim, Norway, August 21-22, 2003, Revised Selected
Papers. Peters, Gonzalo, Braschler, and Kluck, (eds.). LNCS, 3237 /
2004: pp. 672-675. 2004. Springer Verlag
- Bertoldi,
Brugnara, Cettolo, Federico, Giuliani, Leeuwis, Sandrini, "The ITC-irst
News on Demand Platform", Proc. of ECIR 2003, Pisa, Italy, 2003.
- Federico and
Bertoldi, "Statistical Cross-Language Information Retrieval using
N-best Query Translations", in Proc. of ACM SIGIR 2002, Tampere,
Finland, 2002.
- Bertoldi and
Federico, "ITC-irst at CLEF 2002: Using N-best Query Translations for
CLIR", in Peters, Braschler, Gonzalo, and Kluck (Eds.), Advances in
Cross-Language Information Retrieval, pp. 49-58, LNCS 2785, Springer,
Berlin, 2003.
- Federico,
Bertoldi and Sandrini, "Bootstrapping Named Entity Recognition for
Italian Broadcast News", in Proc. of EMNLP 2002, Philadelphia, PA, 2002.
- Federico and
Bertoldi, "Broadcast News LM Adaptation using Contemporary Texts", in
Proc. of EUROSPEECH 2001, Aalborg, Denmark, 2001.
- Bertoldi and
Federico, "Lexical Adaptation for Broadcast News Transcription", Proc.
ISCA ITR Workshop, Sophia-Antipolis, France, 2001.
|
