HLT-mt events

The School of Advanced Technologies for Translators is a two-day course organized by our research group  and targeted to translation students and professionals, language service providers, as well as teachers involved in translators’ training.

Language English

We will participate in WMT 2017 to present:

• 2 research papers:

"Guiding Neural Machine Translation Decoding with External Knowledge"
Rajen Chatterjee, Matteo Negri, Marco Turchi, Marcello Federico, Lucia Specia, and Frédéric Blain

"Multi-Domain Neural Machine Translation through Unsupervised Adaptation"
M. Amin Farajian, Marco Turchi, Matteo Negri, Marcello Federico

Language English

Marcello Federico will be speaker at LocWorld34

Language English

Marcello Federico will be speaker at the TAUS Industry Leader Forum

Language English

Language English

We will participate in EAMT 2017 to present three papers:

"Continuous Learning from Human Post-edits for Neural Machine Translation"
Marco Turchi, Matteo Negri, Amin Farajian and Marcello Federico

"Linguistically Motivated Vocabulary Reduction for Neural Machine Translation"
Duygu Ataman, Matteo Negri, Marco Turchi and Marcello Federico

Language English

Il 7 aprile a Bologna si terrà l'evento "L'italiano al plurale: istruzioni per l'uso" organizzato da AITI (Associazione Italiana Traduttori e Interpreti).

Luisa Bentivogli sarà presente al Tech Corner dell'evento per presentare le tecnologie al servizio dei traduttori sviluppate dall'unità di ricerca HLT-MT.

Language English

Dal 9 all'11 marzo 2017 si svolgerà la seconda edizione del Festival delle Lingue, occasione d'incontro e scambio tra docenti, studenti, famiglie, esperti e formatori.

Marcello Federico e Luisa Bentivogli presenteranno "La traduzione automatica e il futuro della professione del traduttore" (Workshop 32).

  Language English

Paper presentation:

"The IWSLT 2016 Evaluation Campaign"
Mauro Cettolo, Jan Niehues, Sebastian Stuker, Luisa Bentivogli, Roldano Cattoni, Marcello Federico

Poster presentation:

"FBK’s Neural Machine Translation Systems for IWSLT 2016"
M. Amin Farajian, Rajen Chatterjee, Costanza Conforti, Shahab Jalalvand, Vevake Balaraman, Mattia A. Di Gangi, Duygu Ataman, Marco Turchi, Matteo Negri, Marcello Federico

Language English

Symposium in memory of Gianni Lazzari

Language English

Being in graduate school, it seems likely that the most appealing option is to remain in the academic tower. It’s reasonable to see why — the environment you are surrounded with encourages you to follow this career path. However, taking a glance at the Ph.D. labor market proves that the number of PhD graduates annually highly exceeds the number of positions available. In this interactive talk, I first convince you that academia is not the only choice to pursue your career path and brief you on some very interesting research projects in the high-tech industry. Language English

Ontology Learning in the Deep

Language English

Paper presentation: "Online Automatic Post-Editing across Domains"

Language English

Invited presentation: "Context-adaptive Machine Translation system"

Language English

Marcello Federico will present "An Arabic-Hebrew parallel corpus of TED talks" by Mauro Cettolo at the AMTA Workshop on Semitic Machine Translation (SeMaT)

Marcello Federico will present "Machine Translation Adaptation from Translation Memories in ModernMT" at the AMTA Commercial Users Track

Matteo Negri will present "Instance Selection for Online Automatic Post-Editing in a multi-domain scenario" by
Rajen Chatterjee, Mihael Arcan, Matteo Negri and Marco Turchi

Language English

Marcello Federico will present the paper:

Neural versus Phrase-Based Machine Translation Quality: a Case Study
Luisa Bentivogli, Arianna Bisazza, Mauro Cettolo and Marcello Federico

Language English

Marcello federico gives the flash talk "Un cervello artificiale per tradurre" to high school students.

Language English

Language English

A two-day event featuring tutorials on topics in Computational Linguistics.

Language English

Kenneth Heafield is a Lecturer at the University of Edinburgh.
Motivated by machine translation problems, he prefers to build scalable
systems instead of approximating.  He is the author of the KenLM toolkit
that scales statistical language models to trillions of words and runs
Google-scale problems on a single machine.  He completed his PhD at
Carnegie Mellon and worked at Stanford as a postdoctoral scholar.

Language English