Wojciech Łukasiewicz's repositories
20newsgroups-parser
Java utility for parsing the 20 newsgroup dataset
boxer2java
Piece of code that can be used for deserializing the XML Boxer output.
datasketch
MinHash, LSH, LSH Forest, Weighted MinHash, HyperLogLog, HyperLogLog++
dbpedia-spotlight-model
Improving Efficiency and Accuracy in Multilingual Entity Extraction approach
gensim
Topic Modelling for Humans
jest
Delightful JavaScript Testing.
Mallet
MALLET is a Java-based package for statistical natural language processing, document classification, clustering, topic modeling, information extraction, and other machine learning applications to text.
model-quickstarter
Tools and data for creating DBpedia Spotlight models.
sanic-openapi
Easily document your Sanic API with a UI
SEMA4J
Wrapper for easily accessing FrameNet semantic parsing via SEMAFOR parser in Java
snorkel
A system for quickly generating training data with weak supervision
spotlight-demo
HTML and Javascript code to demonstrate DBpedia Spotlight's web service.
topicmodel-extractor
A repository for the "Combining DBpedia and Topic Modeling" GSoC 2016 idea