FinBERT

112 Last view: 2024-04-11

3 Last update: 2021-11-08

finbert-puhti

Persistent Identifier of this resource:

http://urn.fi/urn:nbn:fi:lb-202004212

Access location: http://urn.fi/urn:nbn:fi:lb-2014120218

A version of Google's BERT deep transfer learning model for Finnish. The model can be fine-tuned to achieve state-of-the-art results for various Finnish natural language processing tasks.

It is installed in CSC's Puhti cluster and can be used via the pytorch 1.4 module. For details see /appl/data/kielipankki/bert_models/README.txt

You don’t have the permission to edit this resource.

DistributionAvailability

Available - Restricted Use

Contact Person

User support at CSC - IT Center for Science Ltd. The Language Bank of Finland

toolService

Tool

Language Dependent

Input

Media type: Text

Resource type: Corpus

Modality: Written Language

Language: Finnish

Character encoding: UTF - 8

Output

Media type: Text

Modality: Written Language

Language: Finnish

Character encoding: UTF - 8

Annotation type: Morphosyntactic Annotation - Pos Tagging, Syntactic Annotation - Shallow Parsing

Segmentation level: Clause

Operation

Operating system: Linux

Creation

Formalism: Google BERT

Original Source

Google BERT https://github.com/g...

Metadata

Created: 04/21/2020

Last Updated: 11/08/2021

Revision: Link to resource group page added

Metadata Creator

Ute Dieckmann

Martin Matthiesen

Version

Version: 1.0

Last Updated: 11/25/2019

Documentation

Tool Documentation: Manual, Online

Document Type: Other

Language model source data and documentation on Github, https://github.com/T... , 2020

Publisher: TurkuNLP Group

Keywords: nlp,machine learning

Document Language: English

Document Type: Manual

PyTorch 1.4 documentation, https://pytorch.org/... , 2020

Publisher: Team PyTorch

Keywords: machine learning

Resource group page: http://urn.fi/urn:nb...

Document Type: Other

Hugginface Transformers v.2.5.1 source on Github, https://github.com/h... , 2020

Publisher: Huggingface

People who looked at this resource also viewed the following: