Registered by RelEx Developers

RelEx is an English-language dependency relationship extractor, built on the Carnegie-Mellon link parser. It can identify subject, object, indirect object and many other dependency relationships between words in a sentence. It also generates some advanced semantic relations, such as normalizing questions for question-answering. It also proposes "frames" or "semantic roles", similar in style to those of FrameNet. RelEx includes a basic implementation of the Hobbs anaphora (pronoun) resolution algorithm.

As a "by-product", it also provides more basic functions, including entity detection, part-of-speech tagging, noun-number tagging, verb tense tagging, gender tagging, and so on. Relex now includes a Stanford parser compatibility mode, generating identical output, but more accurately and more quickly.

For a general overview and documentation, please see the main web page at

Source code is now hosted at (the lp:relex repo is no longer used)

The related RelEx-Statistical (AKA LexAt - Lexical Attraction) package is at

Pre-parsed versions of Wikipedia and other texts can be found at

Natural language generation (i.e. inverting what RelEx does) is done by the SegSim/NLGen package at and also by NLGen2

The primary use of RelEx is to support AI applications, and specifically, chat, text comprehension, and general linguistics research within the OpenCog AGI framework.

Interested developers, please drop in at #opencog on the Freenode IRC chat network and/or post to the list at

Project information

Part of:
OpenCog Project
RelEx Developers
OpenCog Developers
Apache Licence

RDF metadata

View full history Series and milestones

trunk series is the current focus of development.

Get Involved

  • Report a bug
  • warning
    Ask a question
  • warning
    Help translate


Latest version is 1.5.1

All downloads