Madrid

Florian Leitner

Expert
@fnl

A polyglot machine learning engineer working on finance, pharma, bio- & fintech projects.

fnl.es

syntok. Text tokenization and sentence segmentation (segtok v2)

210

segtok. Segtok v2 is here: https://github.com/fnl/syntok -- A rule-based sentence segmenter (splitter) and a word tokenizer using orthographic features.

170

pymonad. "fork" of PyMonad on BitBucket to change the ``*`` functor/composition operator to ``<<``

31

patricia-trie. a pure-Python PATRICIA trie implementation.

30

medic. a Python 3 command-line tool to maintain a DB mirror of MEDLINE (https://pypi.python.org/pypi/medic) - ALERT: As I have moved out of science and am working as a consultant now, this project might need a new maintainer once PubMed changes its XML format. Heroes?

25

libfnl. Python 3 tools for data mining in molecular biology

13

progress_bar. an informative progress bar for Python 2+3 command-line tools

12

asdm-tm-class. Course material for the Madrid ASDM class on text mining (C09)

11

classipy. A command-line tool to develop advanced text classifiers using SciKit-Learn.

9

sentence_splitter. check my new spliter - segtok

8

tokenizer. a concurrent, deterministic finite state tokenizer (for letter-based scripts)

4

txtfnnl. a UIMA-based text mining pipeline

3

bootstrap. jump-start a simple GNU C project

2

otplc. A tool to convert corpus annotations between the brat annotation and OTPL formats.

2

go. Golang source code collection

2

SPECIES. a modified version of the SPECIES tagger

2

bceval. BioCreative Evaluation Scripts and Library

2

cpp-project-template. A very basic C++ project structure using CMake, Catch2, and cxxopts.

2

bert. TensorFlow code and pre-trained models for BERT

2

vimrc. my (Vim-centric) POSIX environment

2

couchpy. a python3 library to programmatically access CouchDB (written when there was none, "long ago"...)

2

React-For-Beginners-Starter-Files. Starter files for learning React.js with React for Beginners

1

Capsule-Text-Classification. 利用keras搭建的胶囊网络（capsule network文本分类模型，包含RNN、CNN、HAN等，其中keras_utils包含了capsule层和attention层的keras实现

1

tldr. :books: Simplified and community-driven man pages

1

chemcheck. a syntax checker for BioCreative IV CHEMDNER task annotations

1

libfsmg. A finite state machine library for pattern matching on generic types in Java sequence containers.

1

gnamed. a tool to manage a unified repository of gene and protein names, symbols, keywords, literature references, and species associations

1

ibecs-to-omtd-transformer. A transformer that converts an IBECS XML file into an OMTD-SHARE corpus

1

geniatagger. - part-of-speech tagging, shallow parsing, and named entity recognition for biomedical text -

1

word2numpy. A Python 3.0 port of word2vec.py, in itself a Python 2.7 port of word2vec

1

brat. brat rapid annotation tool (brat) - for all your textual annotation needs

1

OnlineTaggerFramework. an online tagger wrapper for GATE that only spans one global sub-process per processing resource

1

homebrew. The missing package manager for OS X.

1

segmenter. scripts to pre-process plain-text: sentence segmentation, tokenization, and stemming

1

fnl.github.io. my blog (http://fnl.es)

1

lexikos. a minimal acyclic deterministic finite state automaton (MADFA)

1

reactive-programming-scala.

1

factorie. fork to fix the hang when using the socket server for NLP

1

NeuroNER. Named-entity recognition using neural networks. Easy-to-use and state-of-the-art results.

1

fastai. The fast.ai deep learning library, lessons, and tutorials

1
40
Apply