A Danish-speaking language model with entity-aware self-attention

Project description

daLUKE

Implementation of LUKE on Danish text corpus with a focus on named entity recognition.

Installation

pip install daluke

Including optional requirements that are necessary for interacting with datasets and performing analysis:

pip install daluke[full]

Usage

Forward pass simple NER or MLM examples

daluke ner --text "Thomas Delaney fører Danmark til sejr ved EM i fodbold."
daluke masked --text "Slutresultatet af kampen mellem Danmark og Rusland bliver [MASK]-[MASK]."

Project details

Release history Release notifications | RSS feed

0.0.5

Sep 15, 2021

0.0.4

Jul 15, 2021

0.0.3

Jul 3, 2021

This version

0.0.2

Jun 18, 2021

0.0.1.post2

Jun 18, 2021

0.0.1.post1

Jun 18, 2021

0.0.1

Jun 18, 2021

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

daluke-0.0.2.tar.gz (61.2 kB view hashes)

Uploaded Jun 18, 2021 Source

Built Distribution

daluke-0.0.2-py3-none-any.whl (79.1 kB view hashes)

Uploaded Jun 18, 2021 Python 3

Hashes for daluke-0.0.2.tar.gz

Hashes for daluke-0.0.2.tar.gz
Algorithm	Hash digest
SHA256	`9949faa897a19f8e70b54b9d527aa0996b0369feaf85bed2791758e37675226f`
MD5	`ddebd2d998b370612a2fe5d7c9a919cb`
BLAKE2b-256	`022b43c3ca1e8125a13c73a33c085b35b242f1adbfe6ce1e8deb3a8cd5c5ccda`

Hashes for daluke-0.0.2-py3-none-any.whl

Hashes for daluke-0.0.2-py3-none-any.whl
Algorithm	Hash digest
SHA256	`00360fc9d7b96cb6a717f151b5f5f89095c03d7937da962729be43fdbc659235`
MD5	`6cd75b285e86e4516c097bbacf422ed9`
BLAKE2b-256	`a6be8590a007bf682f415c5811e7514db9b3a7277612af6b961b845f7faa423f`