M
Manuel Herranz
Publications - 14
Citations - 61
Manuel Herranz is an academic researcher. The author has contributed to research in topics: Machine translation & Computer science. The author has an hindex of 3, co-authored 10 publications receiving 29 citations.
Papers
More filters
Posted Content
How Much Does Tokenization Affect Neural Machine Translation
Miguel Domingo,Mercedes García-Martínez,Alexandre Helle,Francisco Casacuberta,Manuel Herranz +4 more
TL;DR: The conclusion is reached that the tokenization significantly affects the final translation quality and that the best tokenizer differs for different language pairs.
Posted Content
Incremental Adaptation of NMT for Professional Post-editors: A User Study
Miguel Domingo,Mercedes García-Martínez,Álvaro Peris,Alexandre Helle,Amando Estela,Laurent Bié,Francisco Casacuberta,Manuel Herranz +7 more
TL;DR: This paper conducted a user study on post-editing of a neural machine translation system, which showed a reduction in the required amount of human effort needed when post-ediating the outputs of the system, improvements in the translation quality and a positive perception of the adaptive system by the users.
Large-scale machine translation evaluation of the iADAATPA project
Sheila Castilho,Natália Resende,Federico Gaspari,Andy Way,Tony O'Dowd,Marek Mazur,Manuel Herranz,Alexandre Helle,Gema Ramírez-Sánchez,Víctor M. Sánchez-Cartagena,Marcis Pinnis,Valters Sics +11 more
TL;DR: An evaluation of 34 state-of-the-art domain-adapted machine translation (MT) systems that were built by four leading MT companies as part of the EU-funded iADAATPA project concludes that these systems support a wide variety of languages for several domains.
Incremental Adaptation of NMT for Professional Post-editors: A User Study
Miguel Domingo,Mercedes García-Martínez,Álvaro Peris,Alexandre Helle,Amando Estela,Laurent Bié,Francisco Casacuberta,Manuel Herranz +7 more
TL;DR: A user study on a neural machine translation system, showing a reduction in the required amount of human effort needed when post-editing the outputs of the system, improvements in the translation quality and a positive perception of the adaptive system by the users.
The Multilingual Anonymisation Toolkit for Public Administrations (MAPA) Project
E Ajausks,Victoria Arranz,Laurent Bié,A Cerdà-I-Cucó,Khalid Choukri,Montse Cuadros,Hans Degroote,Amando Estela,Thierry Etchegoyhen,Mercedes García-Martínez,Aitor García-Pablos,Manuel Herranz,Alejandro Adolfo Kohan,Maite Melero,Mike Rosner,Roberts Rozis,Patrick Paroubek,A Vasiļevskis,Pierre Zweigenbaum +18 more
TL;DR: The MAPA project, funded under the Connecting Europe Facility programme, is described, whose goal is the development of an open-source de-identification toolkit for all official European Union languages.