Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Germán Sanchis-Trilles"'
Publikováno v:
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname
instname
[EN] The problem of automatic text classification is an essential part of text analysis. The improvement of text classification can be done at different levels such as a preprocessing step, network implementation, etc. In this paper, we focus on how
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::04e8f6e81beb9ec1b4d9ac949b96dbd2
Publikováno v:
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname
instname
[EN] We present a simple and reliable method for estimating the log-linear weights of a state-of-the-art machine translation system, which takes advantage of the method known as discriminative ridge regression (DRR). Since inappropriate weight estima
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::19a1b2556efb206a07fe6b04d8c57bff
https://doi.org/10.1007/s10044-018-0720-5
https://doi.org/10.1007/s10044-018-0720-5
Autor:
Germán Sanchis-Trilles
Publikováno v:
Machine Translation. 31:251-255
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dd3968f5b6ae88b0e3d74eaec862f39b
https://doi.org/10.1007/s10590-017-9190-6
https://doi.org/10.1007/s10590-017-9190-6
Publikováno v:
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname
instname
[EN] One of the most popular approaches to machine translation consists in formulating the problem as a pattern recognition approach. Under this perspective, bilingual corpora are precious resources, as they allow for a proper estimation of the under
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d647e6e0e73fba0da9d49a4e0cfeb7ed
http://hdl.handle.net/10251/155404
http://hdl.handle.net/10251/155404
Publikováno v:
Advances in Computational Intelligence ISBN: 9783030205201
IWANN (1)
IWANN (1)
In this work we describe a multi-input Convolutional Neural Network for text classification which allows for combining text preprocessed at word level, byte pair encoding level and character level. We conduct experiments on different datasets and we
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5e772615908e511f47010e2cd55cfc2d
https://doi.org/10.1007/978-3-030-20521-8_49
https://doi.org/10.1007/978-3-030-20521-8_49
Publikováno v:
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname
WMT (3)
instname
WMT (3)
[EN] The filtering task of noisy parallel corpora in WMT2019 aims to challenge participants to create filtering methods to be useful for training machine translation systems. In this work, we introduce a noisy parallel corpora filtering system based
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5f64de5e7b25d97ed99e7f6e95af41d2
Publikováno v:
Pattern Recognition and Image Analysis ISBN: 9783319588377
IbPRIA
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname
IbPRIA
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname
[EN] We present a simple and reliable method for estimating the log-linear weights of a state-of-the-art machine translation system, which takes advantage of the method known as discriminative ridge regression (DRR). Since inappropriate weight estima
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c34be1447308fb5245325c4634918fc9
https://doi.org/10.1007/978-3-319-58838-4_4
https://doi.org/10.1007/978-3-319-58838-4_4
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319490540
S+SSPR
S+SSPR
Data selection aims to select the best data subset from an available pool of sentences with which to train a pattern recognition system. In this article, we present a bilingual data selection method that leverages a continuous vector-space representa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3873b7f592d978ee469a61d36efa619c
https://doi.org/10.1007/978-3-319-49055-7_9
https://doi.org/10.1007/978-3-319-49055-7_9
Autor:
Vicente Alabau, Bartolomé Mesa-Lao, Jesús González-Rubio, Michael Carl, Daniel Ortiz-Martínez, Germán Sanchis-Trilles, Moritz Schaeffer, Francisco Casacuberta, Mercedes Garcia Martinez
Publikováno v:
New Directions in Empirical Translation Process Research ISBN: 9783319203577
This chapter reports the results of a longitudinal study (LS14) in which the CASMACAT post-editing workbench was tested with interactive translation prediction (ITP). Whereas previous studies with the CASMACAT workbench (Sanchis-Trilles et al., Machi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6963a8af573079f38ce16a4d59551d32
https://research.cbs.dk/en/publications/a29eb7ea-c365-4b9c-9446-ea8768fcc345
https://research.cbs.dk/en/publications/a29eb7ea-c365-4b9c-9446-ea8768fcc345
Autor:
Germán Sanchis-Trilles, Daniel Ortiz-Martínez, Francisco Casacuberta, Vicent Alabau, Jesús González-Rubio
Publikováno v:
New Directions in Empirical Translation Process Research ISBN: 9783319203577
AMTA (IAMT)
AMTA (IAMT)
This chapter describes a pilot study aiming at testing the integration of online and active learning features into the computer-assisted translation workbench developed within the CASMACAT project. These features can be used to take advantage of the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::02879bec16142bc3e76ca86de94d92dc
https://doi.org/10.1007/978-3-319-20358-4_3
https://doi.org/10.1007/978-3-319-20358-4_3