Computational Linguistics Research Group

news-audit

Fake news detection, Google Summer of Code 2017

MBSP

Memory-based shallow parser for Python

topbox

Python 2 & 3 wrapper around the Stanford Topic Modeling Toolbox. Intended to be used for hassle-free supervised topic classification with Labeled Latent Dirichlet Allocation (L-LDA, LLDA, sLDA).

bratreader

Python code for reading Brat Repositories. Supports saving and reading from XML files for easy acces to annotations.

hades

Repository for the CLiPS HAte speech DEtection System [HADES].

humumls

UMLS in Python with MongoDB.

yarn

Disambiguating biomedical and clinical concepts with word embeddings

memory-networks

Memory networks (and variants) for medical machine reading

srl2tex

Creates LaTeX source from semantic role annotations

english_clinical_modality

Negation and speculation detection of concepts in English clinical text

vardial-dfs

CLiPS submission for the 'Discriminating between Dutch and Flemish in Subtitles' (DFS) subtask at VarDial

gsoc2019_crosslang

GSoC 2019 project on cross language analysis

seg-cnn

Segment CNNs for clinical relation extraction with additional features

patcor

A command and control corpus for the Patience card game (Dutch)

dutchclinicalspeculation

Speculation detection of concepts in Dutch clinical text

gsoc2019_hatespeech