Exploiting semantic roles for asynchronous question answering in an educational setting

  • Authors:

  • Dunwei Wen;John Cuzzola;Lorna Brown; Kinshuk

  • Affiliations:

  • School of Computing and Information Systems, Athabasca University, Athabasca, AB, Canada;School of Computing and Information Systems, Athabasca University, Athabasca, AB, Canada;School of Computing and Information Systems, Athabasca University, Athabasca, AB, Canada;School of Computing and Information Systems, Athabasca University, Athabasca, AB, Canada

  • Venue:
  • Canadian AI'12 Proceedings of the 25th Canadian conference on Advances in Artificial Intelligence
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Recent question answering (QA) research has started to incorporate deep natural language processing (NLP) such as syntactic and semantic parsing in order to enhance the capability of selecting the most relevant answers to a given question. However, current NLP technology involves intensive computing and thus hard to meet the real-time demand of synchronous QA. To improve e-learning we introduce NLP into a QA system that specifically exploits the communication latency between student and instructor. We present how the system will fit for educational environment, and how semantic similarity matching between a question and its candidate answers can be improved by semantic roles. The designed system and its running results show the perspective and potential of this research.