Skip to main navigation
Skip to search
Skip to main content
Maastricht University Home
Support & FAQ
Link opens in a new tab
Search content at Maastricht University
Home
Researchers
Publications
Activities
Press/Media
Prizes
Organisations
Dataset/Software
Projects
Optimizing segmentation granularity for neural machine translation
Elizabeth Salesky
*
, Andrew Runge
, Alex Coda
, Jan Niehues
, Graham Neubig
*
Corresponding author for this work
Department of Advanced Computing Sciences
Research output
:
Contribution to journal
›
Article
›
Academic
›
peer-review
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Optimizing segmentation granularity for neural machine translation'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Granularity
100%
Neural Machine Translation
100%
Subword
66%
Subword Units
66%
Grid Search
66%
Byte Pair Encoding
66%
Web-based
33%
Performance Improvement
33%
Training Effectiveness
33%
Training Time
33%
Training Performance
33%
Suboptimal Performance
33%
Accuracy Improvement
33%
Efficiency Improvement
33%
Resource Constraints
33%
Small Units
33%
Hyperparameters
33%
Rare Words
33%
Validation Loss
33%
Open-vocabulary
33%
INIS
optimization
100%
units
100%
machine translations
100%
resources
40%
performance
40%
grids
40%
validation
20%
efficiency
20%
losses
20%
accuracy
20%
constraints
20%
tuning
20%
Computer Science
Granularity
100%
Machine Translation
100%
Performance Improvement
33%
Optimal Performance
33%
Resource Constraint
33%
Leaning Parameter
33%
Engineering
Granularity
100%
Grid Search
66%
Performance Improvement
33%
Optimal Performance
33%