Educational Question Answering Motivated by Question-Specific Concept Maps
Question answering (QA) is the automated process of answering general questions submitted by humans in natural language. QA has previously been explored within the educational context to facilitate learning, however the majority of works have focused on text-based answering. As an alternative, this paper proposes an approach to return answers as a concept map, which further encourages meaningful learning and knowledge organisation. Additionally, this paper investigates whether adapting the returned concept map to the specific question context provides further learning benefit. A randomised experiment was conducted with a sample of 59 Computer Science undergraduates, obtaining statistically significant results on learning gain when students are provided with the question-specific concept maps. Further, time spent on studying the concept maps were positively correlated with the learning gain.
KeywordsConcept mapping Educational question answering NLP
Unable to display preview. Download preview PDF.
- 1.Katz, B. Annotating the world wide web using natural language. In: Fifth RIAO Conference on Computer Assisted Information Searching on the Internet (1997)Google Scholar
- 2.Gurevych, I., et al., Educational question answering based on social media content. In: Proceedings of the 2009 conference on Artificial Intelligence in Education, p. 133-140 (2009)Google Scholar
- 3.Novak, J.D., Canas, A.J.: The Theory underlying Concept maps and How to construct and use them. Florida Institute for Human and Machine Cognition (2006)Google Scholar
- 4.Dali, L., et al.: Question answering based on semantic graphs. In: Language and Technology Conference, Poznan (2009)Google Scholar
- 5.Bloom, B., et al., Taxonomy of educational objectives: the classification of educational goals. In: Handbook I: Cognitive Domain, New York, Toronto (1956)Google Scholar
- 6.Atapattu, T., Falkner, K. Falkner, N.: Acquistion of triples of knowledge from lecture notes: a natural langauge processing approach. In: 7th International Conference on Educational Data Mining, London (2014)Google Scholar
- 7.Atapattu, T., Falkner, K., Falkner, N.: Evaluation of Concept Importance in Concept Maps Mined from Lecture Notes: Computer vs Human. In 6th International Conference on Computer Supported Education, Barcelona (2014)Google Scholar
- 9.Kolomiyets, O., Moens, M.: A survey on question answering technology from an information retrieval perspective. Information Sciences 181(24) (2011)Google Scholar
- 10.Manning, C., et al.: The stanford CoreNLP natural language processing toolkit. In: 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, Baltimore (2014)Google Scholar
- 12.Canas, A.J., et al.: CmapTools: a knowledge modeling and sharing environment. In: First International Conference on Concept Mapping, Pamplona (2004)Google Scholar
- 13.Gallagher, B.: Matching structure and semantics: A survey on graph-based pattern matching. AAAI FS 6, 45–53 (2006)Google Scholar
- 14.Kenny, D.A.: Statistics for the Social and Behavioural Sciences (1987)Google Scholar