Zobrazeno 1 - 10
of 110
pro vyhledávání: '"David Vilar"'
Autor:
Ranaboldo, Matteo, Lega, Bruno Domenech, Ferrenbach, David Vilar, Ferrer-Martí, Laia, Moreno, Rafael Pastor, García-Villoria, Alberto
Publikováno v:
In Applied Energy 1 April 2014 118:280-291
Publikováno v:
Findings of the Association for Computational Linguistics: ACL 2022.
Publikováno v:
Findings of the Association for Computational Linguistics: EMNLP 2021.
Autor:
David Vilar, Marcello Federico
Publikováno v:
IWSLT
Sub-word segmentation is currently a standard tool for training neural machine translation (MT) systems and other NLP tasks. The goal is to split words (both in the source and target languages) into smaller units which then constitute the input and o
Autor:
Matt Post, David Vilar
Publikováno v:
NAACL-HLT
The end-to-end nature of neural machine translation (NMT) removes many ways of manually guiding the translation process that were available in older paradigms. Recent work, however, has introduced a new capability: lexically constrained or guided dec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::44965de01f1d239e72d8356f31bf5a47
http://arxiv.org/abs/1804.06609
http://arxiv.org/abs/1804.06609
Autor:
David Vilar
Publikováno v:
NAACL-HLT (2)
In this paper we explore the use of Learning Hidden Unit Contribution for the task of neural machine translation. The method was initially proposed in the context of speech recognition for adapting a general system to the specific acoustic characteri
Shield wire systems running along existing high-voltage transmission lines can supply household electricity to communities located within 20 km of the high-voltage corridor. At a fraction of the cost of new substations or independent medium-voltage l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6f33fbdf2fba50a4eee3ad0a23e2cbce
https://doi.org/10.1596/28620
https://doi.org/10.1596/28620
Autor:
Mitsunori Motohashi, Richard Hosier, David Vilar de Ferrenbach, Morgan Bazilian, Tatia Lemondzhava, Kabir Malik
This report evaluates the use of rural electrification concessions in Africa. It provides a comprehensive overview of successful and failed cases and identifies the likely factors behind successes. The research was conducted in three stages. First, a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::df1a3db6749819e85a6c5e91ec47aec9
https://doi.org/10.1596/27476
https://doi.org/10.1596/27476
Publikováno v:
Machine Translation. 26:197-216
In this article we will describe the design and implementation of Jane, an efficient hierarchical phrase-based (HPB) toolkit developed at RWTH Aachen University. The system has been used by RWTH at several international evaluation campaigns, includin
Autor:
Hermann Ney, David Vilar
Publikováno v:
Machine Translation. 26:217-254
In this article we present two novel enhancements for the cube pruning and cube growing algorithms, two of the most widely applied methods when using the hierarchical approach to statistical machine translation. Cube pruning is the de facto standard