You are here

Nicola Bertoldi

  • SKYPE: nicola.bertoldi
  • Phone: +39 0461314560
  • FBK Povo
Short bio

I got my PhD in Mathematics at Department of Mathematics, U. Trento, Italy in 2005 discussing the dissertation "Statistical Models and Search Algorithms for Machine Translation" (Advisors: Prof. Roberto Battiti, and Dr. Marcello Federico). I have been a permanent researcher at FBK, formerly ITC, since 2008 in the Human Language Technologies (HLT) research unit. From 2000 and 2007 I had worked as a contract researcher in the same group. My research interests are in the field of multilingual Natural Language Processing with special interest in Machine Translation of both text and speech, Computer Assisted Translation, and language Modeling. Previous research activities regarded Information Retrieval and Speech Translation. I was and actually am involved in several projects funded by the European Community or by the regional governments. I co-authored more than 60 scientific publications and have served as reviewer international journals, conferences and workshops. I taught several computer science modules as assistant professor at the universities of Trento and Bolzano.

Present Projects: MateCat, MosesCore

Past Projects: CoreTex, TC-STAR, EuroMatrixPlus, WebFAQ, AINEVA, MeteoTrentino. ATLAS

Research interests
Machine Translation Computer Assisted Translation Speech Translation Language Modeling Natural Language Processing
  1. Marcello Federico; Nicola Bertoldi,
    Broadcast News LM Adaptation using Contemporary Texts,
    International Conference Acoustics, Speech and Signal Processing (ICASSP),
    , pp. 239-
    , (International Conference Acoustics, Speech and Signal Processing (ICASSP),
    Salt Lake City, UT, USA,
  2. Nicola Bertoldi,
    Studio ed implementazione di modelli statistici per il problema del POS Tagging,
  3. Nicola Bertoldi; Marcello Federico,
    Italian Text Retrieval for CLEF 2000 at ITC-irst,
    This paper presents work on document retrieval for Italian carried out at ITC-irst. Two different approaches to information retrieval were investigated, one based on the Okapi weighting formula and one based on a statistical model. Development experiments were carried out using the Italian sample of the TREC-8 CLIR track. Performance evaluation was done on the Cross Language Evaluation Forum (CLEF) 2000 Italian monolingual track,