CoreNLP: A Java suite of core NLP tools for tokenization, sentence segmentation, NER, parsing, coreference, sentiment analysis, etc.

Fluxtream Web Application and Core Modules

You've stumbled on my undergraduate thesis proejct. This project takes raw Wikipedia articles as input and outputs a knowledge graph wherein "entities" (people, places, events) are nodes and vertic…

The main goal of this project is to build machine learning and information retrieval tools, which use 100GB of Wikipedia data for models training. See bellow what goals have been achieved.