Skip to main content Link Search Menu Expand Document (external link)

Reading and knowledge assembly software


Eidos is the machine reading system developed by the CLU lab at University of Arizona. This repository includes the reading software as well as code for integrating with DART.

Concept Discovery

This is the concept identification component, which is used by the ontology-in-a-day (OIAD) system.


Hume is BBN’s machine reading system that extracts CAGs and supports the OIAD clustering. It leverages the following software

Text-Open contains Java and Python APIs for reading and writing BBN’s SerifXML format, which is BBN’s internal representation of documents and information.

LearnIt is a tool for customizing Machine Readers (a.k.a., Information Extraction algorithms) with human in the loop. Within WM, we also use it as a pattern-based extractor for event extraction.

NLPLingo is BBN’s Deep Learning toolkit for event extraction and causal relation extraction.

CSerif contains C/C++ code for pre-reading of texts into BBN’s SerifXML format. We are working on open sourcing this.


Within the reading/assembly ecosystem Causemos has the following components:

Causemos HMI

Causemos knowledge pipeline

Causemos data pipeline, for BYOD infrastructure

Causemos schemas and mappings

Causemos recommendation/curation service




The reading and assembly software developed under World Modelers program share the same underlying ontology.