Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Computer aided language translation"'
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 shared encoder-decoder. In this paper, we propose an alternative approach based on language-specific encoder-decoders, which can be easily extended to new languages by learning their corre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::698e223a8017acd4d2c195874cd9acba
https://hdl.handle.net/2117/368571
https://hdl.handle.net/2117/368571
Autor:
Görgün, Onur, Yıldız, Olcay Taner
This study extends our initial efforts in building an English-Turkish parallel treebank corpus for statistical machine translation tasks. We manually generated parallel trees for about 17K sentences selected from the Penn Treebank corpus. English sen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______3401::491c479f9e372f4814515d01db29ccdc
https://hdl.handle.net/11729/3421
https://hdl.handle.net/11729/3421
Neural Machine Translation (NMT) is one of the advanced approaches of Machine Translation (MT) that has recently gained popularity. A significant amount of parallel corpus is required to achieve a sound translation system, but most languages have a d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::65e452fc5a7da9312b00f8cf024a2292
https://hdl.handle.net/2117/387209
https://hdl.handle.net/2117/387209
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
We give an update on the Found in Translation (FoTran) project, focusing on the study of emerging language-agnostic representations from neural machine translation (NMT). We describe our attention-bridge model, a modular NMT model which connects lang
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1299::e1887a8a88fcc00ae104dc5576dcc470
http://hdl.handle.net/10281/394431
http://hdl.handle.net/10281/394431
Autor:
Hasan Bulut, Emre Satir
Publikováno v:
INISTA
Kocaeli University;Kocaeli University Technopark
2021 International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2021 -- 25 August 2021 through 27 August 2021 -- -- 172175
Phrase-based models are among the best
2021 International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2021 -- 25 August 2021 through 27 August 2021 -- -- 172175
Phrase-based models are among the best
Publikováno v:
Volume: 27, Issue: 1 437-452
Turkish Journal of Electrical Engineering and Computer Science
Turkish Journal of Electrical Engineering and Computer Science
In this paper, we present our English-to-Turkish translation methodology, which adopts a tree-based approach. Our approach relies on tree analysis and the application of structural modification rules to get the target side (Turkish) trees from source
Publikováno v:
Computational Linguistics. 43:683-722
In this article, we explore the potential of using sentence-level discourse structure for machine translation evaluation. We first design discourse-aware similarity measures, which use all-subtree kernels to compare discourse parse trees in accordanc
Publikováno v:
29th Pacific Asia Conference on Language, Information and Computation, PACLIC 2015
29th Pacific Asia Conference on Language, Information and Computation, PACLIC 2015, Oct 2015, Shangai, China. pp.106-115
29th Pacific Asia Conference on Language, Information and Computation, PACLIC 2015, Oct 2015, Shangai, China. pp.106-115
Conference of 29th Pacific Asia Conference on Language, Information and Computation, PACLIC 2015 ; Conference Date: 30 October 2015 Through 1 November 2015; Conference Code:119467; International audience; In this paper, we study the impact of using a
Publikováno v:
EMNLP
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
The encoder-decoder framework for neural machine translation (NMT) has been shown effective in large data scenarios, but is much less effective for low-resource languages. We present a transfer learning method that significantly improves BLEU scores
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::31037bb149192c9db1c17d6ca2c3ffd4
http://arxiv.org/abs/1604.02201
http://arxiv.org/abs/1604.02201