Share This Author
Interactive neural machine translation
The CLIN27 Shared Task: Translating Historical Text to Contemporary Language for Improving Automatic Linguistic Annotation
The CLIN27 shared task evaluates the effect of translating historical text to modern text with the goal of improving the quality of the output of contemporary natural language processing tools appl…
How Much Does Tokenization Affect Neural Machine Translation?
- Miguel Domingo, Mercedes García-Martínez, A. Helle, F. Casacuberta, Manuel Herranz
- Computer ScienceArXiv
- 20 December 2018
The conclusion is reached that the tokenization significantly affects the final translation quality and that the best tokenizer differs for different language pairs.
Segment-based interactive-predictive machine translation
This work presents one of these new interactive protocols, which allows the user to validate all correct word sequences in a translation hypothesis, and compares it against the classical prefix-based approach.
Spelling normalization of historical documents by using a machine translation approach
Three approaches are proposed—based on statistical, neural and character-based machine translation— to adapt the document’s spelling to modern standards to create a digital text version of a historical document.
Interactive-Predictive Translation Based on Multiple Word-Segments
This work proposes a new interactive protocol which allows the user to validate all correct word sequences in the translation generated by the system, breaking the left-to-right barrier.
Incremental Adaptation of NMT for Professional Post-editors: A User Study
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.
Demonstration of a Neural Machine Translation System with Online Learning for Translators
An end-to-end platform integrating machine translation servers to one of the most common user interfaces for professional translators: SDL Trados Studio is implemented, to save post-editing effort as the machine is continuously learning from its mistakes and adapting the models to a specific domain or user style.
Historical Documents Modernization
- Miguel Domingo, Mara Chinea-Rios, F. Casacuberta
- Sociology, Computer SciencePrague Bull. Math. Linguistics
- 1 June 2017
This method is based in statistical machine translation, and aims at translating historical documents into a modern version of their original language, obtaining very encouraging results.
A Machine Translation Approach for Modernizing Historical Documents Using Backtranslation
In this work, several machine translation approaches for modernizing historical documents are proposed and tested in different scenarios, obtaining very encouraging results.