23 |
Czech image captioning, machine translation, and sentiment analysis (Neural Monkey models)
|
|
|
|
BASE
|
|
Show details
|
|
24 |
Training Tips for the Transformer Model
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 110, Iss 1, Pp 43-70 (2018) (2018)
|
|
Abstract:
This article describes our experiments in neural machine translation using the recent Tensor2Tensor framework and the Transformer sequence-to-sequence model (Vaswani et al., 2017). We examine some of the critical parameters that affect the final translation quality, memory usage, training stability and training time, concluding each experiment with a set of recommendations for fellow researchers. In addition to confirming the general mantra “more data and larger models”, we address scaling to multiple GPUs and provide practical tips for improved training regarding batch size, learning rate, warmup steps, maximum sentence length and checkpoint averaging. We hope that our observations will allow others to get better results given their particular hardware and data constraints.
|
|
Keyword:
Computational linguistics. Natural language processing; P98-98.5
|
|
URL: https://doi.org/10.2478/pralin-2018-0002 https://doaj.org/article/1635d185bebf4ceda1ed71b5beba511d
|
|
BASE
|
|
Hide details
|
|
25 |
Universal Dependencies 2.1
|
|
|
|
In: https://hal.inria.fr/hal-01682188 ; 2017 (2017)
|
|
BASE
|
|
Show details
|
|
29 |
Universal Dependencies 2.0 – CoNLL 2017 Shared Task Development and Test Data
|
|
|
|
BASE
|
|
Show details
|
|
31 |
CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
|
|
|
|
BASE
|
|
Show details
|
|
36 |
QTLeap WSD/NED corpus
|
|
Agirre, Eneko; Branco, António; Popel, Martin. - : University of the Basque Country, UPV/EHU, 2015. : Faculty of Science, Univeristy of Lisbon, FCUL, 2015. : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2015. : Bulgarian Academy of Sciences, IICT-BAS, 2015
|
|
BASE
|
|
Show details
|
|
38 |
Europarl QTLeap WSD/NED corpus
|
|
Agirre, Eneko; Branco, António; Popel, Martin. - : University of the Basque Country, UPV/EHU, 2015. : Faculty of Science, Univeristy of Lisbon, FCUL, 2015. : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2015. : Bulgarian Academy of Sciences, IICT-BAS, 2015
|
|
BASE
|
|
Show details
|
|
40 |
MT-ComparEval: Graphical evaluation interface for Machine Translation development
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 104, Iss 1, Pp 63-74 (2015) (2015)
|
|
BASE
|
|
Show details
|
|
|
|