Search Results for author: Francisco Casacuberta

Found 34 papers, 12 papers with code

A Machine Translation Approach for Modernizing Historical Documents Using Backtranslation

no code implementations IWSLT (EMNLP) 2018 Miguel Domingo, Francisco Casacuberta

This makes historical documents to be hard to comprehend by contemporary people and, thus, limits their accessibility to scholars specialized in the time period in which a certain document was written.

Machine Translation Translation

NICE: Neural Integrated Custom Engines

no code implementations EAMT 2020 Daniel Marín Buj, Daniel Ibáñez García, Zuzanna Parcheta, Francisco Casacuberta

In this paper, we present a machine translation system implemented by the Translation Centre for the Bodies of the European Union (CdT).

Machine Translation Translation

A User Study of the Incremental Learning in NMT

no code implementations EAMT 2020 Miguel Domingo, Mercedes García-Martínez, Álvaro Peris, Alexandre Helle, Amando Estela, Laurent Bié, Francisco Casacuberta, Manuel Herranz

Adaptive neural machine translation systems, able to incrementally update the underlying models under an online learning regime, have been proven to be useful to improve the efficiency of this workflow.

Incremental Learning Machine Translation +2

Introducing Mouse Actions into Interactive-Predictive Neural Machine Translation

no code implementations MTSummit 2021 Ángel Navarro, Francisco Casacuberta

The quality of the translations generated by Machine Translation (MT) systems has highly improved through the years and but we are still far away to obtain fully automatic high-quality translations.

Machine Translation Translation

Two Demonstrations of the Machine Translation Applications to Historical Documents

1 code implementation2 Feb 2021 Miguel Domingo, Francisco Casacuberta

Once the user is satisfied with the system's hypothesis and validates it, the system adapts its model following an online learning strategy.

Machine Translation online learning +1

An Interactive Machine Translation Framework for Modernizing Historical Documents

no code implementations8 Oct 2019 Miguel Domingo, Francisco Casacuberta

Modernization aims at breaking this language barrier by generating a new version of a historical document, written in the modern version of the document's original language.

Machine Translation Translation

Filtering of Noisy Parallel Corpora Based on Hypothesis Generation

no code implementations WS 2019 Zuzanna Parcheta, Germ{\'a}n Sanchis-Trilles, Francisco Casacuberta

The filtering task of noisy parallel corpora in WMT2019 aims to challenge participants to create filtering methods to be useful for training machine translation systems.

Machine Translation Translation

Modernizing Historical Documents: a User Study

no code implementations1 Jul 2019 Miguel Domingo, Francisco Casacuberta

This is due to the language barrier inherent in human language and the linguistic properties of these documents.

Machine Translation Translation

Interactive-predictive neural multimodal systems

no code implementations30 May 2019 Álvaro Peris, Francisco Casacuberta

We show that, following this framework, we approximately halve the effort spent for correcting the outputs generated by the automatic systems.

Machine Translation Translation +1

How Much Does Tokenization Affect Neural Machine Translation?

no code implementations20 Dec 2018 Miguel Domingo, Mercedes Garcıa-Martınez, Alexandre Helle, Francisco Casacuberta, Manuel Herranz

Separating punctuation and splitting tokens into words or subwords has proven to be helpful to reduce vocabulary and increase the number of examples of each word, improving the translation quality.

Machine Translation Translation +1

Active Learning for Interactive Neural Machine Translation of Data Streams

1 code implementation CONLL 2018 Álvaro Peris, Francisco Casacuberta

We study the application of active learning techniques to the translation of unbounded data streams via interactive neural machine translation.

Active Learning Machine Translation +1

NMT-Keras: a Very Flexible Toolkit with a Focus on Interactive NMT and Online Learning

1 code implementation9 Jul 2018 Álvaro Peris, Francisco Casacuberta

We present NMT-Keras, a flexible toolkit for training deep learning models, which puts a particular emphasis on the development of advanced applications of neural machine translation systems, such as interactive-predictive translation protocols and long-term adaptation of the translation system via continuous learning.

General Classification Machine Translation +6

Online Learning for Effort Reduction in Interactive Neural Machine Translation

1 code implementation10 Feb 2018 Álvaro Peris, Francisco Casacuberta

We show that a neural machine translation system can be rapidly adapted to a specific domain, exclusively by means of online learning techniques.

Machine Translation online learning +1

Egocentric Video Description based on Temporally-Linked Sequences

1 code implementation7 Apr 2017 Marc Bolaños, Álvaro Peris, Francisco Casacuberta, Sergi Soler, Petia Radeva

We propose a novel methodology that exploits information from temporally neighboring events, matching precisely the nature of egocentric sequences.

Video Description

Video Description using Bidirectional Recurrent Neural Networks

1 code implementation12 Apr 2016 Álvaro Peris, Marc Bolaños, Petia Radeva, Francisco Casacuberta

Although traditionally used in the machine translation field, the encoder-decoder framework has been recently applied for the generation of video and image descriptions.

Text Generation Translation +2

Online optimisation of log-linear weights in interactive machine translation

no code implementations LREC 2014 Mara Chinea Rios, Germ{\'a}n Sanchis-Trilles, Daniel Ortiz-Mart{\'\i}nez, Francisco Casacuberta

Whenever the quality provided by a machine translation system is not enough, a human expert is required to correct the sentences provided by the machine translation system.

Language Modelling Machine Translation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.