WARNING: Website under maintenance!!!
What is Ascent?

Ascent (Advanced Semantics for Commonsense Knowledge Extraction) is a pipeline for automatically collecting, extracting and consolidating commonsense knowledge (CSK) from the web. Ascent is capable of extracting facet-enriched assertions, overcoming the common limitations of the triple-based knowledge model in traditional knowledge bases (KBs). Ascent also captures composite concepts with subgroups and related aspects, supplying even more expressiveness to CSK assertions.

An example of Ascent's knowledge for the concept elephant can be seen in the following figure, in which the novel part of our model over traditional methods is marked inside the green box.

The web interface

This demo gives you an interface to explore a commonsense knowledge base extracted by the Ascent pipeline. We executed for 10,000 prominent concepts in ConceptNet. The resulting KB contains more than 284,000 subgroups and 92,000 related aspects, with 8.6 million assertions and 4.4 million facets in total.

You can also try playing with our Commonsense Question Answering demo.


To explore what AscentKB captures, browse the following concepts:

Or try out the search functionality.