no code implementations • MTSummit 2021 • Alexandra Birch, Barry Haddow, Antonio Valerio Miceli Barone, Jindrich Helcl, Jonas Waldendorf, Felipe Sánchez Martínez, Mikel Forcada, Víctor Sánchez Cartagena, Juan Antonio Pérez-Ortiz, Miquel Esplà-Gomis, Wilker Aziz, Lina Murady, Sevi Sariisik, Peggy van der Kreeft, Kay Macquarrie
We find that starting from an existing large model pre-trained on 50languages leads to far better BLEU scores than pretraining on one high-resource language pair with a smaller model.
no code implementations • LREC (BUCC) 2022 • Rik van Noord, Cristian García-Romero, Miquel Esplà-Gomis, Leopoldo Pla Sempere, Antonio Toral
An important goal of the MaCoCu project is to improve EU-specific NLP systems that concern their Digital Service Infrastructures (DSIs).
no code implementations • EAMT 2020 • Felipe Sánchez-Martínez, Víctor M. Sánchez-Cartagena, Juan Antonio Pérez-Ortiz, Mikel L. Forcada, Miquel Esplà-Gomis, Andrew Secker, Susie Coleman, Julie Wall
This paper describes our approach to create a neural machine translation system to translate between English and Swahili (both directions) in the news domain, as well as the process we followed to crawl the necessary parallel corpora from the Internet.
no code implementations • WMT (EMNLP) 2020 • Miquel Esplà-Gomis, Víctor M. Sánchez-Cartagena, Jaume Zaragoza-Bernabeu, Felipe Sánchez-Martínez
This paper describes the joint submission of Universitat d’Alacant and Prompsit Language Engineering to the WMT 2020 shared task on parallel corpus filtering.
no code implementations • EAMT 2022 • Marta Bañón, Miquel Esplà-Gomis, Mikel L. Forcada, Cristian García-Romero, Taja Kuzman, Nikola Ljubešić, Rik van Noord, Leopoldo Pla Sempere, Gema Ramírez-Sánchez, Peter Rupnik, Vít Suchomel, Antonio Toral, Tobias van der Werff, Jaume Zaragoza
We introduce the project “MaCoCu: Massive collection and curation of monolingual and bilingual data: focus on under-resourced languages”, funded by the Connecting Europe Facility, which is aimed at building monolingual and parallel corpora for under-resourced European languages.
no code implementations • 13 Mar 2024 • Rik van Noord, Taja Kuzman, Peter Rupnik, Nikola Ljubešić, Miquel Esplà-Gomis, Gema Ramírez-Sánchez, Antonio Toral
Large, curated, web-crawled corpora play a vital role in training language models (LMs).
1 code implementation • 29 Jan 2024 • Víctor M. Sánchez-Cartagena, Miquel Esplà-Gomis, Juan Antonio Pérez-Ortiz, Felipe Sánchez-Martínez
When the amount of parallel sentences available to train a neural machine translation is scarce, a common practice is to generate new synthetic training samples from them.
1 code implementation • 16 Jan 2024 • Miquel Esplà-Gomis, Víctor M. Sánchez-Cartagena, Juan Antonio Pérez-Ortiz, Felipe Sánchez-Martínez
The paper presents an automatic evaluation of these techniques on four language pairs that shows that our approach can successfully exploit monolingual texts in a TM-based CAT environment, increasing the amount of useful translation proposals, and that our neural model for estimating the post-editing effort enables the combination of translation proposals obtained from monolingual corpora and from TMs in the usual way.
1 code implementation • EMNLP 2021 • Víctor M. Sánchez-Cartagena, Miquel Esplà-Gomis, Juan Antonio Pérez-Ortiz, Felipe Sánchez-Martínez
Many DA approaches aim at expanding the support of the empirical data distribution by generating new sentence pairs that contain infrequent words, thus making it closer to the true data distribution of parallel sentences.
Data Augmentation Low-Resource Neural Machine Translation +3
1 code implementation • EMNLP (IWSLT) 2019 • Carolina Scarton, Mikel L. Forcada, Miquel Esplà-Gomis, Lucia Specia
To that end, we report experiments on a dataset with newly-collected post-editing indicators and show their usefulness when estimating post-editing effort.
no code implementations • WS 2018 • Miquel Esplà-Gomis, Felipe Sánchez-Martínez, Mikel L. Forcada
We describe the Universitat d'Alacant submissions to the word- and sentence-level machine translation (MT) quality estimation (QE) shared task at WMT 2018.