Zobrazeno 1 - 10 of 136 pro vyhledávání: '"Rodríguez Fonollosa, José Adrián"'
1
Multilingual machine translation: Closing the gap between shared and language-specific encoder-decoders
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
Zobrazit plný text záznamu
2
The TALP-UPC participation in WMT21 news translation task: an mBART-based NMT approach
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)
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
Zobrazit plný text záznamu
3
Multilingual machine translation: Closing the gap between shared and language-specific encoder-decoders
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)
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
Zobrazit plný text záznamu
4
Syntax-driven iterative expansion language models for controllable text generation
Autor: Casas Manzanares, Noé, Rodríguez Fonollosa, José Adrián, Ruiz Costa-Jussà, Marta
Publikováno v: UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
The dominant language modeling paradigm handles text as a sequence of discrete tokens. While that approach can capture the latent structure of the text, it is inherently constrained to sequential dynamics for text generation. We propose a new paradig
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::5f84f3b9f079d55b5efaeba96674f797
http://hdl.handle.net/2117/341494
Zobrazit plný text záznamu
5
Automatic Spanish translation of SQuAD dataset for multi-lingual question answering
Autor: Carrino, Casimiro Pio, Ruiz Costa-Jussà, Marta, Rodríguez Fonollosa, José Adrián
Publikováno v: UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Recently, multilingual question answering became a crucial research topic, and it is receiving increased interest in the NLP community.However, the unavailability of large-scale datasets makes it challenging to train multilingual QA systems with perf
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::4657ed00b537a5d5594504802bc14a3f
https://hdl.handle.net/2117/329270
Zobrazit plný text záznamu
6
The TALP-UPC system description for WMT20 news translation task: multilingual adaptation for low resource MT
Autor: Escolano Peinado, Carlos, Ruiz Costa-Jussà, Marta, Rodríguez Fonollosa, José Adrián
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
Zobrazit plný text záznamu
7
The UPC RDF-to-Text System at WebNLG Challenge 2020
Autor: Bergés Lladó, David, Cantenys Sabà, Roser, Creus Castanyer, Roger, Domingo Roig, Oriol, Rodríguez Fonollosa, José Adrián|||0000-0001-9513-7939
Publikováno v: UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
This work describes the end-to-end system architecture presented at WebNLG Challenge 2020. The system follows the traditional Machine Translation (MT) pipeline, based on the Transformer model, applied in most text-to-text problems. Our solution is en
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::034fa5f4986d0a8ce143b7fa466fd442
https://hdl.handle.net/2117/366164
Zobrazit plný text záznamu
8
Combining subword representations into word-level representations in the transformer architecture
Autor: Casas Manzanares, Noé, Ruiz Costa-Jussà, Marta, Rodríguez Fonollosa, José Adrián
Publikováno v: UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
In Neural Machine Translation, using word-level tokens leads to degradation in translation quality. The dominant approaches use subword-level tokens, but this increases the length of the sequences and makes it difficult to profit from word-level info
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::3ea448596e5a75ef19f0aa815043e544
http://hdl.handle.net/2117/330587
Zobrazit plný text záznamu
9
The TALP-UPC system description for WMT20 news translation task: multilingual adaptation for low resource MT
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)
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
Zobrazit plný text záznamu
10
A differentiable BLEU loss. Analysis and first results
Autor: Casas Manzanares, Noé, Rodríguez Fonollosa, José Adrián, Ruiz Costa-Jussà, Marta
Publikováno v: UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Recercat. Dipósit de la Recerca de Catalunya
instname
In natural language generation tasks, like neural machine translation and image captioning, there is usually a mismatch between the optimized loss and the de facto evaluation criterion, namely token-level maximum likelihood and corpus-level BLEU scor
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::3bb98ed13c0fefcdc5c33cca13a3d2aa
https://hdl.handle.net/2117/117201
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje