Publications

Authors: Frédéric Blain (LIUM), Amir Hazem (LIUM), Fethi Bougares (LIUM), Loic Barrault (LIUM), Holger Schwenk (LIUM). Abstract: Computer assisted translation (CAT) tools, which are designed to support and facilitate the translation process play an important role to boost the productivity

Authors: Mauro Cettolo (FBK), Nicola Bertoldi (FBK), Marcello Federico (FBK). Abstract: . Italian Computational Linguistics Conference. Pisa, Italy, December 2014. To appear Download the full paper

Authors: José G. C. de Souza (FBK – University of Trento), Marco Turchi (FBK), Matteo Negri (FBK), Antonis Anastasopoulos (National Technical University of Athens). Abstract: . Italian Computational Linguistics Conference. Pisa, Italy, December 2014. To appear Download the full paper

Authors: Nicola Bertoldi (FBK), Patrick Simianer (University of Heidelberg), Mauro Cettolo (FBK), Katharina Waeschle (University of Heidelberg), Marcello Federico (FBK), Stefan Riezler (University of Heidelberg). Abstract: Recent research has shown that accuracy and speed of human translators can benet from post-editing

Authors: Marco Turchi (FBK), Matteo Negri (FBK), Marcello Federico (FBK). Abstract:  . Machine Translation Journal. To appear. Download the full paper

Authors: Mauro Cettolo (FBK), Nicola Bertoldi (FBK), Marcello Federico (FBK), Holger Schwenk (LIUM), Loic Barrault (LIUM), Christophe Servan (LIUM). Abstract: The effective integration of MT technology into computer-assisted translation tools is a challenging topic both for academic research and the

Authors: Kyunghyun Cho, Bart van Merriënboer, Caglar Gulcehre (University of Montreal), Dzmitry Bahdanau (Jacobs University), Fethi Bougares, Holger Schwenk (LIUM), Yoshua Bengio (University of Montreal). Abstract: In this paper, we propose a novel neural network model called RNN Encoder–Decoder that consists

Authors: Marcello Federico (FBK), Matteo Negri (FBK), Luisa Bentivogli (FBK), Marco Turchi (FBK). Abstract: Learning from errors is a crucial aspect of improving expertise. Based on this notion, we discuss a robust statistical framework for analysing the impact of different

Authors: Ulrich Germann (UEDIN). Abstract: This paper presents a phrase table implementation for the Moses system that computes phrase table entries for phrase-based statistical machine translation (PBSMT) on demand by sampling an indexed bitext. While this approach has been used for

Authors: Prashant Mathur (FBK – University of Trento), Mauro Cettolo (FBK). Abstract: In this paper we propose a cascading framework for optimizing online learning in machine translation for a computer assisted translation scenario. With the use of online learning, several hyperparameters