Abstract
Question classification is an important part of several tasks, especially in educational systems. In this paper, we present a system that classifies questions asked in an educational context based on the expected characteristics of answers, with a future goal to facilitate the analysis of student responses. To this end, we propose an approach that employs a deep neural network together with features tailored to each question type (expected answer characteristic), word embeddings and inter-class dependency features. To demonstrate the effectiveness of the proposed method, we use a corpus of questions collected from real science classrooms and augment it with data from online resources from the same domain. Our approach achieves a weighted \(F_1\)-score of 0.678, outperforming the baseline by 56%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bloom, B.S.: Taxonomy of Educational Objectives: The Classification of Educational Goals: Cognitive Domain. Longman, New York (1956)
Conner, M.: What a reference librarian should know. Libr. J. 52(8), 415–418 (1927)
Crews, K.D.: The accuracy of reference service: Variables for research and implementation. Libr. Inf. Sci. Res. 10(3), 331–355 (1988)
Curto, S., Mendes, A.C., Coheur, L.: Question generation based on lexico-syntactic patterns learned from the web. Dialogue Discourse 3(2), 147–175 (2012)
Godea, A., Nielsen, R.: Annotating educational questions for student response analysis. In: 11th Edition of the Language Resources and Evaluation Conference (2018)
Harabagiu, S.M., Moldovan, D.I., Paşca, M., Mihalcea, R., Surdeanu, M., Bunescu, R., Gîrju, C.R., Rus, V., Morărescu, P.: FALCON: Boosting knowledge for answer engines (2000)
Hovy, E., Hermjakob, U., Ravichandran, D.: A question/answer typology with surface text patterns. In: Proceedings of the Second International Conference on Human Language Technology Research, pp. 247–251. Morgan Kaufmann Publishers Inc. (2002)
Ä°nce, Ä°.F.: Intellegent question classification for e-learning environments by data mining techniques. Ph.D. thesis, Institute of Science (2008)
Li, X., Roth, D.: Learning question classifiers. In: Proceedings of the 19th International Conference on Computational Linguistics, vol. 1, pp. 1–7. Association for Computational Linguistics (2002)
Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. EMNLP 14, 1532–1543 (2014)
Radev, D., Fan, W., Qi, H., Wu, H., Grewal, A.: Probabilistic question answering on the web. J. Assoc. Inf. Sci. Technol. 56(6), 571–583 (2005)
Team, D.D.: Deeplearning4j: open-source distributed deep learning for the JVM, apache software foundation license 2.0. (2017). http://deeplearning4j.org
Acknowledgements
This research was supported by the Institute of Education Sciences, U.S. Department of Education, Grant R305A120808 to University of North Texas. Opinions expressed are those of the authors.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Godea, A., Tulley-Patton, D., Barbee, S., Nielsen, R. (2018). Classifying Educational Questions Based on the Expected Characteristics of Answers. In: Penstein Rosé, C., et al. Artificial Intelligence in Education. AIED 2018. Lecture Notes in Computer Science(), vol 10948. Springer, Cham. https://doi.org/10.1007/978-3-319-93846-2_20
Download citation
DOI: https://doi.org/10.1007/978-3-319-93846-2_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-93845-5
Online ISBN: 978-3-319-93846-2
eBook Packages: Computer ScienceComputer Science (R0)