This is your work, valued
vim-256noir. A dark 256-color colorscheme for vim
196pyre2. Python wrapper for RE2
108roaringbitmap. Roaring Bitmap in Cython
82readability. Measure the readability of a given text using surface characteristics
81disco-dop. Discontinuous Data-Oriented Parsing
47dutchcoref. Dutch coreference resolution & dialogue analysis using deterministic rules
23seekaywhy. A probabilistic CKY parser for PCFGs
19eodop. Data-Oriented Parsing implementation for NLTK applied to Esperanto morphology and syntax
10cplay. curses front-end for various audio players
9pdfbrowse. A simple AJAX PDF viewer and browser
8subsequences. Extract longest common subsequences from texts
7codingforhumanities. Coding for Humanities course materials
7fictiongenres. Code and data for the chapter "Computational Methods for the Analysis of Fiction Genres"
6fmindex. Efficient substring searches on text corpora using a compressed index
6activedop. A treebank annotation tool based on a statistical parser that is re-trained during annotation
5critbit. Critbit trees in C
5literariness. Code for the paper "A data-oriented model of literary language"
4crac2020. Code for e2e coref model in Dutch
4litvecspace. Accompanying code for the paper "Vector space explorations of literary language"
4tgrep2. Fork of tgrep2
3kinglit. Code for the paper "Stylometric Literariness Classification: the Case of Stephen King"
3ethnlpgender. Code for paper "Bias and Fairness in Authorial Gender Attribution"
3dop-transformations. Transformations with Data-Oriented Parsing
3qrinductionsplit. Splitting qualitative process models as produced by model induction using a behavior graph
3authident. Authorship attribution with syntactic fragments
2diction. diction / style UNIX utitlities
2udstyle. Compute complexity metrics from Universal Dependencies
2litquest. Code and data for LaTeCH 2020 paper on a literariness questionnaire
1dutchlitpreproc. Preprocessing pipeline for Dutch literature
1sdsl-lite. Succinct Data Structure Library 2.0
1berkeley-coreference-analyser. A tool for classifying errors in coreference resolution
1neuralspellnorm. Jupyter Notebook
1strongweaklit. Code and data for the chapter "Dutch Strong and Weak Pronouns as a Stylistic Marker of Literariness"
1cython. A Python to C compiler
1spacyconllu. Simple script to parse text with spaCy and print the output in CoNLL-U format.
1litcliches. Code for the paper "Cliche expressions in literary and genre novels"
1openboek. The OpenBoek corpus
1