Computational Linguistics and & Text Mining Lab's repositories
multilingual-wiki-event-pipeline
This project aims to extract information about incidents of a particular type. This information consists of structured data on the incidents from Wikidata, as well as unstructured description and supporting sources from Wikipedia. We obtain information from Wikipedia in multiple languages.
vu-rm-pip3
Dutch NewsReader pipeline
WordnetTools
Set of functions to use a wordnet in Wordnet-LMF format
ma-course-subjectivity-mining
Repository for the Subjectivity mining course
pepper_tensorflow
This is the repository for Pepper modules and external services. Use Python 3
ma-tm-domains-SDG-tracker
Text Mining, Master project for the Text Mining Domains course, 2020
probing-cross-linqual-model
This is a code base for the paper WordNet View on Crosslingual Contextual Language Models
refnews
RefNews-12 dataset
frame-annotation-tool
Annotation tool in JavaScript and Node.js for annotation of frames in Dutch documents.
Target-Spans-Detection
Target_Spans_HateXplain
inner-outer-coreference
A repository for investigating the role of common ground in datasets of social dialogue in coreference resolution tasks
voc-missives
NER and format conversion scripts for the Generale Missiven
nafparserpy
lightweight lxml wrapper for NAF
FrameNet_annotations_on_SoNaR
files annotated with framenet frames and roles
ODWN_Reader
The goal of this repository is to load Referentie Bestand Nederland into Python classes as well as compute descriptive statistics.