You are here
News HLT-nlp, HLT-mt
"Modern MT: A New Open-Source Machine Translation Platform for the Translation Industry"
U. Germann, E. Barbu, L. Bentivogli, N. Bertoldi, N. Bogoychev, C. Buck, D. Caroselli, L. Carvalho, A. Cattelan, R. Cattoni, M. Cettolo, M. Federico, B. Haddow, D. Madl, L. Mastrostefano, P. Mathur, A. Ruopp, A. Samiotou, V. Sudharshan, M. Trombetti, J. van der Meer
"An Unsupervised Method for Automatic Translation Memory Cleaning"
Masoud Jalili Sabet, Matteo Negri, Marco Turchi and Eduard Barbu
"First Shared Task on Automatic Translation Memory Cleaning: Preparation and Lessons Learned"
Eduard Barbu, Carla Parra Escartín, Luisa Bentivogli, Matteo Negri, Marco Turchi, Marcello Federico, Luca Mastrostefano, Constantin Orasan
"The IWSLT Evaluation Campaign: Challenges, Achievements, Future Directions"
Luisa Bentivogli, Marcello Federico, Sebastian Stüker, Mauro Cettolo, Jan Niehues
"WAGS: A Beautiful English-Italian Benchmark Supporting Word Alignment Evaluation on Rare Words"
Luisa Bentivogli, Mauro Cettolo, M. Amin Farajian, Marcello Federico.
In the contest of Evalita 2016, we are co-organizing FactA (Event Factuality Annotation), the first evaluation exercise for factuality profiling of events in Italian.
Title: Identifying User Issues and Request Types in Forum Question Posts based on Discourse Analysis
Authors: Agnes Sandor, Nikolaos Lagos, Ngoc Phuoc An Vo, Caroline Brun.
"MEANTIME, the NewsReader Multilingual Event and Time Corpus", "Annotating opposition relations among Italian verb senses using crowdsourcing", "Classifying Temporal Relations with Simple Features", and "Corpora for Learning the Mutual Relationship between Semantic Relatedness and Textual Entailment"
A. Bisazza, M. Federico, "A Survey of Word Reordering in Statistical Machine Translation: Computational Models and Language Phenomena", Computational Linguistics, 2016. (Accepted for publication)Language English
L. Bentivogli, N. Bertoldi, M. Cettolo, M. Federico, M. Negri, M. Turchi, "Evaluation of Adaptive Machine Translation for Human Post-Editing"
has been accepted for publication in the IEEE/ACM Transactions on Audio, Speech, and Language Processing.Language English
Vivi Nastase and Carlo Strapparava. knoWitiary: A Machine Readable Incarnation of Wiktionary. International Journal of Computational Linguistics and Applications. Vol. 6 No. 2 - December 2015
Sebastian Stüker presents on behalf of Marcello the overview paper:
Mauro Cettolo, Jan Niehues, Sebastian Stüker, Luisa Bentivogli and Marcello Federico
Report on the 12th IWSLT Evaluation Campaign, IWSLT 2015
12th International Workshop on Spoken Language Translation, Da Nang, Vietnam, 2015Language English
Presentation by Josè at the Second Italian Conference on Computational Linguistics of the work:
Hamed Zamani, Josè G. C. de Souza, Matteo Negri, Marco Turchi and Daniele Falavigna
"Reference-free and Confidence-independent Binary Quality Estimation for Automatic Speech Recognition"Language English
Marco Trombetti and Marcello Federico presented a tutorial on machine translation and the MateCat tool at the 37th Translating and the Computer Conference, in London.
- Cross-language projection of multilayer semantic annotation in the NewsReader Wikinews Italian Corpus (WItaC)
- FacTA: Evaluation of Event Factuality and Temporal Anchoring
- Annotating opposition among verb senses: a crowdsourcing experiment
Two papers were presented at the MT Summit XV (Miami, Florida, October 30 – November 3, 2015).Language English
Marcello Federico presented the MMT project at the TAUS Annual Conference, 12-13 October 2015, San Josè, California.Language English
Authors: Asma Ben Abacha, Md Faisal Mahmub Chowdhury, Aikaterini Karanasiou, Yassine Mrabet, Alberto Lavelli, Pierre Zweigenbaum
Our students Josè Camargo de Souza, Nick Ruiz and Amin Farajian participated to the Google NLP PhD Summit 2015, held at Google Zurich on 23 - 26 September 2015.Language English
Marcello Federico attended the Facebook Faculty Summit that was held in London on 22 Sept 2015. About 100 people were invited to the meeting, including FB people from USA and Europe and externals from Europe. The meeting was organised in four separate tracks: machine learning, security, programming languages, and systems. The purpose of the meeting was to update participants about FB's research agenda and activities and to foster collaborations with the invited researchers. MF gave a short presentation about the ideas developed in MateCat and the MMT project.Language English