Skip to main navigation
Skip to search
Skip to main content
University of Copenhagen Research Portal Home
Help & FAQ
Dansk
English
Home
Profiles
Research output
Research units
Press/Media
Activities
Prizes
???studenttheses???
Datasets
Search by expertise, name or affiliation
Improving historical spelling normalization with bi-directional LSTMs and multi-task learning
Marcel Bollman,
Anders Søgaard
Department of Computer Science
19
Citations (Scopus)
59
Downloads (Pure)
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Improving historical spelling normalization with bi-directional LSTMs and multi-task learning'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Spelling Normalization
100%
Multi-task Learning
100%
Bidirectional Long Short-term Memory (BiLSTM)
100%
Normalization Data
50%
Character-level
50%
Early New High German
50%
Computer Science
Bidirectional Long Short-Term Memory Network
100%
Multitask Learning
100%
Deep Neural Network
50%
Neural Network Architecture
50%