Publications

@article{Benstead2023,
title = {An inter-specialty cancer training programme curriculum for Europe},
author = {Kim Benstead AND Andreas Brandl AND Ton Brouwers AND Jorge Civera AND Sarah Collen AND Degi L. Csaba AND Johan De Munter AND Marieke Dewitte AND Diez de los Rios, Celia AND Nikolina Dodlek AND Jesper G. Eriksen AND Patrice Forget AND Chiara Gasparatto AND Jan Geissler AND Corinne Hall AND Alfons Juan AND Marco Kalz AND Richard Kelly AND Giorgos Klis AND Taibe Kulaksiz AND Carine Lecoq AND Francesca Marangoni AND Wendy McInally AND Kathy Oliver AND Maria Popovics AND Christos Poulios AND Richard Price AND Irena Rollo AND Silvia Romeo AND Jana Steinbacher AND Virpi Sulosaari AND Niall O’Higgins},
doi = {10.1016/j.ejso.2023.106989 },
year = {2023},
date = {2023-07-28},
journal = {European Journal of Surgical Oncology},
volume = {49},
number = {9},
pages = {106989},
abstract = {INTRODUCTION: Multidisciplinary and multi-professional collaboration is vital in providing better outcomes for patients The aim of the INTERACT-EUROPE Project (Wide Ranging Cooperation and Cutting Edge Innovation As A Response To Cancer Training Needs) was to develop an inter-specialty curriculum. A pilot project will enable a pioneer cohort to acquire a sample of the competencies needed. METHODS: A scoping review, qualitative and quantitative surveys were undertaken. The quantitative survey results are reported here. Respondents, including members of education boards, curriculum committees, trainee committees of European specialist societies and the ECO Patient Advisory Committee, were asked to score 127 proposed competencies on a 7-point Likert scale as to their value in achieving the aims of the curriculum. Results were discussed and competencies developed at two stakeholder meetings. A consultative document, shared with stakeholders and available online, requested views regarding the other components of the curriculum. RESULTS: Eleven competencies were revised, three omitted and three added. The competencies were organised according to the CanMEDS framework with 13 Entrustable Professional Activities, 23 competencies and 127 enabling competencies covering all roles in the framework. Recommendations regarding the infrastructure, organisational aspects, eligibility of trainees and training centres, programme contents, assessment and evaluation were developed using the replies to the consultative document. CONCLUSIONS: An Inter-specialty Cancer Training Programme Curriculum and a pilot programme with virtual and face-to-face components have been developed with the aim of improving the care of people affected by cancer.},
keywords = {educational technologies, Neural Machine Translation},
pubstate = {published},
tppubtype = {article}
}

@phdthesis{Arnal2023,
title = {Transformer models for Machine Translation and Streaming Automatic Speech Recognition},
author = {Baquero Arnal, Pau},
url = {https://doi.org/10.4995/Thesis/10251/193680
https://www.upv.es/pls/oalu/sic_ted.mostrar_tesis?p_num_reg=12917},
year = {2023},
date = {2023-01-01},
school = {Universitat Politècnica de València},
abstract = {Natural language processing (NLP) is a set of fundamental computing prob- lems with immense applicability, as language is the natural communication vehicle for people. NLP, along with many other computer technologies, has been revolutionized in recent years by the impact of deep learning. This thesis is centered around two keystone problems for NLP: machine translation (MT) and automatic speech recognition (ASR); and a common deep neural architec- ture, the Transformer, that is leveraged to improve the technical solutions for some MT and ASR applications. ASR and MT can be utilized to produce cost-effective, high-quality multilin- gual texts for a wide array of media. Particular applications pursued in this thesis are that of news translation or that of automatic live captioning of tele- vision broadcasts. ASR and MT can also be combined with each other, for instance generating automatic translated subtitles from audio, or augmented with other NLP solutions: text summarization to produce a summary of a speech, or speech synthesis to create an automatic translated dubbing, for in- stance. These other applications fall out of the scope of this thesis, but can profit from the contributions that it contains, as they help to improve the performance of the automatic systems on which they depend. This thesis contains an application of the Transformer architecture to MT as it was originally conceived, achieving state-of-the-art results in similar language translation. In successive chapters, this thesis covers the adaptation of the Transformer as a language model for streaming hybrid ASR systems. After- wards, it describes how we applied the developed technology for a specific use case in television captioning by participating in a competitive challenge and achieving the first position by a large margin. We also show that the gains came mostly from the improvement in technology capabilities over two years including that of the Transformer language model adapted for streaming, and the data component was minor.},
note = {Advisors: Alfons Juan Ciscar and Hermann Ney},
keywords = {Automatic Speech Recognition, Neural Machine Translation, Transformer, Transformer Language Model},
pubstate = {published},
tppubtype = {phdthesis}
}

@inproceedings{Iranzo-Sánchez2019,
title = {The MLLP-UPV Supervised Machine Translation Systems for WMT19 News Translation Task},
author = {Iranzo-Sánchez, Javier and Garcés Díaz-Munío, Gonçal V. and Civera, Jorge and Juan, Alfons},
url = {https://www.mllp.upv.es/wp-content/uploads/2019/09/poster-1.pdf},
doi = {10.18653/v1/W19-5320},
year = {2019},
date = {2019-01-01},
booktitle = {Proc. of Fourth Conference on Machine Translation (WMT19)},
pages = {218-224},
address = {Florence (Italy)},
abstract = {[EN] This paper describes the participation of the MLLP research group of the Universitat Politècnica de València in the WMT 2019 News Translation Shared Task. In this edition, we have submitted systems for the German ↔ English and German ↔ French language pairs, participating in both directions of each pair. Our submitted systems, based on the Transformer architecture, make ample use of data filtering, synthetic data and domain adaptation through fine-tuning.

[CA] "Els sistemes de traducció automàtica supervisada de l'MLLP-UPV per a la tasca de traducció de notícies de WMT19": En aquest article descrivim la participació del grup de recerca MLLP de la Universitat Politècnica de València en la competició de traducció de notícies de WMT 2019. En aquesta edició, hem presentat sistemes per a les combinacions de traducció alemany ↔ anglés i alemany ↔ francés (en ambdós sentits). Els sistemes presentats, basats en l'arquitectura Transformer, fan un ús extens del filtratge de dades, les dades sintètiques i l'ajust fi amb adaptació al domini.},
keywords = {Machine Translation, Neural Machine Translation, WMT19 News Translation},
pubstate = {published},
tppubtype = {inproceedings}
}

@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}
}

@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}
}