Advanced Semantics for Commonsense Knowledge Extraction

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.

Publications

  • Tuan-Phong Nguyen, Simon Razniewski, Gerhard Weikum. Advanced Semantics for Commonsense Knowledge Extraction. WWW 2021. [pdf]
  • Tuan-Phong Nguyen, Simon Razniewski, Gerhard Weikum. Inside ASCENT: Exploring a Deep Commonsense Knowledge Base and its Usage in Question Answering. ACL 2021 - System Demonstrations. [pdf]