Open Source Register: Overzicht

Browser based post correction tool for Alto XML files

Annif is a multi-algorithm automated classification and subject indexing tool for libraries, archives and museums. This repository is used for developing a production version of the system, based on ideas from the initial prototype.

Reports about the experiments using Annif

Automatic subject assignment for KB ebooks using Annif.

😀😄😂😭 A curated list of Sentiment Analysis methods, implementations and misc. 😥😟😱😤

Book back recognition

Pytorch-Named-Entity-Recognition-with-BERT

Automatic metadating: assigning Brinkman keywords

The data and code accomanying my research master thesis: Exploring text mining techniques tostructure a digitised catalogue.

Scripts and data for creating test CDs using different CD layouts

The data and the annotations from crowdsourcing are stored in this repository.

Classified Historical Newspaper Images

Entity linker for the newspaper collection of the National Library of the Netherlands. Links named entity mentions to DBpedia descriptions using either a binary SVM classifier or a neural net.

Web interface to manually annotate named entity mentions in newspaper articles with the correct DBpedia link(s), if any. Produces labeled data sets for training and evaluating the DAC Entity Linker.

Scripts to work with the Public Domain files of DBNL: https://www.dbnl.org/letterkunde/pd/index.php

KB RiR project to Collect a corpus of Dutch novels 1800-2000 and Investigate Canonicity

Scripts to scrape DBNL and work with the texts.

XML transformation from DBNL to DraCor format

Collection of Python scripts to build a Solr index from selected Dutch and English DBpedia dumps.