|
| | | | |
| | | |
| Stat |
Members: 3645
Articles: 2'501'711
Articles rated: 2609
20 April 2024 |
|
| | | | |
|
Article overview
| |
|
|
Competence-based Curriculum Learning for Neural Machine Translation | | Emmanouil Antonios Platanios
; Otilia Stretcu
; Graham Neubig
; Barnabas Poczos
; Tom M. Mitchell
; | | Date: |
26 Mar 2019 | | Abstract: | Current state-of-the-art NMT systems use large neural networks that are not
only slow to train, but also often require many heuristics and optimization
tricks, such as specialized learning rate schedules and large batch sizes. This
is undesirable as it requires extensive hyperparameter tuning. In this paper,
we propose a curriculum learning framework for NMT that reduces training time,
reduces the need for specialized heuristics or large batch sizes, and results
in overall better performance. Our framework consists of a principled way of
deciding which training samples are shown to the model at different times
during training, based on the estimated difficulty of a sample and the current
competence of the model. Filtering training samples in this manner prevents the
model from getting stuck in bad local optima, making it converge faster and
reach a better solution than the common approach of uniformly sampling training
examples. Furthermore, the proposed method can be easily applied to existing
NMT models by simply modifying their input data pipelines. We show that our
framework can help improve the training time and the performance of both
recurrent neural network models and Transformers, achieving up to a 70%
decrease in training time, while at the same time obtaining accuracy
improvements of up to 2.2 BLEU. | | Source: | arXiv, 1903.9848 | | Services: | Forum | Review | PDF | Favorites | |
|
|
No review found.
Did you like this article?
Note: answers to reviews or questions about the article must be posted in the forum section.
Authors are not allowed to review their own article. They can use the forum section.
browser Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)
|
| |
|
|
|
|
News, job offers and information for researchers and scientists:
| |
REGISTER