Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Escolano Peinado, Carlos"'
Autor:
Escolano Peinado, Carlos
Publikováno v:
TDX (Tesis Doctorals en Xarxa)
TDR. Tesis Doctorales en Red
Consejo Superior de Investigaciones Científicas (CSIC)
TDR. Tesis Doctorales en Red
Consejo Superior de Investigaciones Científicas (CSIC)
This thesis aims to study different language-specific approaches for Multilingual Machine Translation without parameter sharing and their properties compared to the current state-of-the-art based on parameter-sharing. We define Multilingual Machine T
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::35ad82e225a3622d8440f0814a2e4196
https://hdl.handle.net/10803/6739822117/365523
https://hdl.handle.net/10803/6739822117/365523
Autor:
Ferrando Monsonís, Javier, Gallego Olsina, Gerard Ion, Alastruey Lasheras, Belen, Escolano Peinado, Carlos, Ruiz Costa-jussà, Marta
In Neural Machine Translation (NMT), each token prediction is conditioned on the source sentence and the target prefix (what has been previously translated at a decoding step). However, previous work on interpretability in NMT has mainly focused sole
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c7fad6711c8d768b37198bc9ed28fd11
Publikováno v:
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Universitat Politècnica de Catalunya (UPC)
This thesis aims to study different language-specific approaches for Multilingual Machine Translation without parameter sharing and their properties compared to the current state-of-the-art based on parameter-sharing. We define Multilingual Machine T
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=RECOLECTA___::376698973af53eb1a1968d1fcd4fae90
http://hdl.handle.net/2117/365523
http://hdl.handle.net/2117/365523
Autor:
Escolano Peinado, Carlos, Ruiz Costa-Jussà, Marta, Rodríguez Fonollosa, José Adrián, Artetxe Zurutuza, Mikel
State-of-the-art multilingual machine translation relies on a universal encoder-decoder, which requires retraining the entire system to add new languages. In this paper, we propose an alternative approach that is based on language-specific encoder-de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______3484::21d0ddcada25e832dca305063ce33619
https://hdl.handle.net/2117/347326
https://hdl.handle.net/2117/347326
Autor:
Escolano Peinado, Carlos|||0000-0001-6657-673X, Tsiamas, Ioannis|||0000-0003-1049-2515, Basta, Christine Raouf Saad, Ferrando Monsonís, Javier|||0000-0002-2637-0961, Ruiz Costa-Jussà, Marta|||0000-0002-5703-520X, Rodríguez Fonollosa, José Adrián|||0000-0001-9513-7939
Publikováno v:
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Universitat Politècnica de Catalunya (UPC)
This paper describes the submission to the WMT 2021 news translation shared task by the UPC Machine Translation group. The goal of the task is to translate German to French (De-Fr) and French to German (Fr-De). Our submission focuses on fine-tuning a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::be95bbdad3ff6a155574abb39eefcd13
https://hdl.handle.net/2117/365972
https://hdl.handle.net/2117/365972
Autor:
Escolano Peinado, Carlos|||0000-0001-6657-673X, Ruiz Costa-Jussà, Marta|||0000-0002-5703-520X, Rodríguez Fonollosa, José Adrián|||0000-0001-9513-7939, Artetxe Zurutuza, Mikel
Publikováno v:
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Universitat Politècnica de Catalunya (UPC)
State-of-the-art multilingual machine translation relies on a universal encoder-decoder, which requires retraining the entire system to add new languages. In this paper, we propose an alternative approach that is based on language-specific encoder-de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=RECOLECTA___::ca12b6c234f060d3ebe4f9a6b2e06ac3
http://hdl.handle.net/2117/347326
http://hdl.handle.net/2117/347326
In this article, we describe the TALP-UPC participation in the WMT20 news translation shared task for Tamil-English. Given the low amount of parallel training data, we resort to adapt the task to a multilingual system to benefit from the positive tra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______3484::24b5f1c728f01e6b08e0a3006d729bb3
https://hdl.handle.net/2117/341255
https://hdl.handle.net/2117/341255
Autor:
Ruiz Costa-Jussà, Marta, Escolano Peinado, Carlos, Basta, Christine Raouf Saad, Ferrando Monsonís, Javier, Batlle, Roser, Kharitonova, Ksenia
Publikováno v:
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Universitat Politècnica de Catalunya (UPC)
Multilingual Neural Machine Translation architectures mainly differ in the amount of sharing modules and parameters among languages. In this paper, and from an algorithmic perspective, we explore if the chosen architecture, when trained with the same
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::20c485690b89efa1043695dbe3a36c88
http://hdl.handle.net/2117/348079
http://hdl.handle.net/2117/348079
Autor:
Escolano Peinado, Carlos|||0000-0001-6657-673X, Ruiz Costa-Jussà, Marta|||0000-0002-5703-520X, Rodríguez Fonollosa, José Adrián|||0000-0001-9513-7939
Publikováno v:
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Universitat Politècnica de Catalunya (UPC)
In this article, we describe the TALP-UPC participation in the WMT20 news translation shared task for Tamil-English. Given the low amount of parallel training data, we resort to adapt the task to a multilingual system to benefit from the positive tra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=RECOLECTA___::095c09b5bb59cbe396efd0be2cb70f94
http://hdl.handle.net/2117/341255
http://hdl.handle.net/2117/341255
Autor:
Escolano Peinado, Carlos|||0000-0001-6657-673X, Ruiz Costa-Jussà, Marta|||0000-0002-5703-520X, Lacroux, Elora, Vázquez Alcocer, Pere Pau|||0000-0003-4638-4065
Publikováno v:
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Universitat Politècnica de Catalunya (UPC)
The main alternatives nowadays to dealwith sequences are Recurrent Neural Net-works (RNN), Convolutional Neural Networks(CNN) architectures and the Transformer. Inthis context, RNN’s, CNN’s and Transformerhave most commonly been used as an encode
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=RECOLECTA___::ad8ec77ca34d5de33aed045dac8936cb
http://hdl.handle.net/2117/184198
http://hdl.handle.net/2117/184198