Quality information extraction at web scale. Edit

Given a scholarly PDF, extract figures, tables, captions, and section titles.

Science Parse parses scientific papers (in PDF form) and returns them in structured form.

NLP toolkit (tokenizer, POS-tagger, parser, etc.)

SBT Plugins for AI2 projects

Easily identify and label sentence intervals using various taggers.

A collection of useful utility classes and functions.

A scala wrapper for OpenRegex.

Store for immutable objects in S3

Word2Vec Java Port

A corpus retrieval engine based on Apache Lucene

TuffyLite is an open-source MLN inference engine that modifies the original Tuffy solver.