Publications

@inproceedings{Baquero-Arnal2019,
title = {The MLLP-UPV Spanish-Portuguese and Portuguese-Spanish Machine Translation Systems for WMT19 Similar Language Translation Task},
author = {Baquero-Arnal, Pau and Iranzo-Sánchez, Javier and Civera, Jorge and Juan, Alfons},
url = {https://www.aclweb.org/anthology/W19-5423/
https://www.mllp.upv.es/wp-content/uploads/2019/09/poster-2.pdf},
year = {2019},
date = {2019-01-01},
booktitle = {Proc. of Fourth Conference on Machine Translation (WMT19)},
pages = {179-184},
address = {Florence (Italy)},
abstract = {This paper describes the participation of the MLLP research group of the Universitat Politècnica de València in the WMT 2019 Similar Language Translation Shared Task. We have submitted systems for the Portuguese ↔ Spanish language pair, in both directions. They are based on the Transformer architecture, as well as on a novel architecture called 2D alternating RNN. Both systems have been domain adapted through fine-tuning which has been shown to be very effective.},
keywords = {Machine Translation, Neural Machine Translation, WMT19},
pubstate = {published},
tppubtype = {inproceedings}
}

@article{Miró2018,
title = {Multilingual videos for MOOCs and OER},
author = {Valor Miró, Juan Daniel and Pau Baquero-Arnal and Jorge Civera and Carlos Turró and Alfons Juan},
url = {https://www.mllp.upv.es/wp-content/uploads/2019/11/JETS2018MLLP.pdf
https://www.j-ets.net/collection/published-issues/21_2},
year = {2018},
date = {2018-01-01},
journal = {Journal of Educational Technology & Society},
volume = {21},
number = {2},
pages = {1--12},
abstract = {Massive Open Online Courses (MOOCs) and Open Educational Resources (OER) are rapidly growing, but are not usually offered in multiple languages due to the lack of cost-effective solutions to translate the different objects comprising them and particularly videos. However, current state-of-the-art automatic speech recognition (ASR) and machine translation (MT) techniques have reached a level of maturity which opens the possibility of producing multilingual video subtitles of publishable quality at low cost. This work summarizes authors' experience in exploring this possibility in two real-life case studies: a MOOC platform and a large video lecture repository. Apart from describing the systems, tools and integration components employed for such purpose, a comprehensive evaluation of the results achieved is provided in terms of quality and efficiency. More precisely, it is shown that draft multilingual subtitles produced by domain-adapted ASR/MT systems reach a level of accuracy that make them worth post-editing, instead of generating them ex novo, saving approximately 25%–75% of the time. Finally, the results reported on user multilingual data consumption reflect that multilingual subtitles have had a very positive impact in our case studies boosting student enrolment, in the case of the MOOC platform, by 70% relative.},
keywords = {Machine Translation, MOOCs, multilingual, Speech Recognition, video lecture repositories},
pubstate = {published},
tppubtype = {article}
}

@inproceedings{Iranzo-Sánchez2018,
title = {The MLLP-UPV German-English Machine Translation System for WMT18},
author = {Iranzo-Sánchez, Javier and Baquero-Arnal, Pau and Garcés Díaz-Munío, Gonçal V. and Martínez-Villaronga, Adrià and Civera, Jorge and Juan, Alfons},
url = {http://dx.doi.org/10.18653/v1/W18-6414
https://www.mllp.upv.es/wp-content/uploads/2018/11/wmt18_mllp-upv_poster.pdf},
year = {2018},
date = {2018-01-01},
booktitle = {Proc. of the Third Conference on Machine Translation (WMT18), Volume 2: Shared Task Papers},
pages = {422--428},
address = {Brussels (Belgium)},
abstract = {[EN] This paper describes the statistical machine translation system built by the MLLP research group of Universitat Politècnica de València for the German>English news translation shared task of the EMNLP 2018 Third Conference on Machine Translation (WMT18). We used an ensemble of Transformer architecture–based neural machine translation systems. To train our system under "constrained" conditions, we filtered the provided parallel data with a scoring technique using character-based language models, and we added parallel data based on synthetic source sentences generated from the provided monolingual corpora.

[CA] "El sistema de traducció automàtica alemany>anglés de l'MLLP-UPV per a WMT18": En aquest article descrivim el sistema de traducció automàtica estadística creat pel grup d'investigació MLLP de la Universitat Politècnica de València per a la competició de traducció de notícies alemany>anglés de la Third Conference on Machine Translation (WMT18, associada a la conferència EMNLP 2018). Hem utilitzat una combinació de sistemes de traducció automàtica neuronal basats en l'arquitectura Transformer. Per a entrenar el nostre sistema en la categoria "fitada" (només amb els corpus lingüístics oficials de la competició), hem filtrat les dades paral·leles disponibles amb una tècnica que assigna puntuacions utilitzant models de llenguatge de caràcters, i hem afegit dades paral·leles basades en frases d'origen sintètiques generades a partir dels corpus monolingües disponibles.},
keywords = {Data Selection, Machine Translation, Neural Machine Translation, WMT18 news translation},
pubstate = {published},
tppubtype = {inproceedings}
}