×

zbMATH — the first resource for mathematics

Algorithm for predicting mathematical formulae from linear strings for mathematical inputs. (English) Zbl 1395.97002
Kotsireas, Ilias S. (ed.) et al., Applications of computer algebra, Kalamata, Greece, July 20–23, 2015. Cham: Springer (ISBN 978-3-319-56930-7/hbk; 978-3-319-56932-1/ebook). Springer Proceedings in Mathematics & Statistics 198, 137-148 (2017).
Summary: Recently, computer-aided assessment (CAA) systems have been used for mathematics education, with some CAA systems capable of assessing learners’ answers using mathematical expressions. However, the standard input method for mathematics education systems is cumbersome for novice learners. In 2011, we proposed a new mathematical input method that allowed users to input mathematical expressions through an interactive conversion of mathematical expressions from colloquial-style linear strings in WYSIWYG. In this study, we propose a predictive algorithm to improve the input efficiency of this conversion process by using machine learning to determine the score parameters with a structured perceptron similar to natural language processing. In our experimental evaluation, with a training dataset comprising 700 formulae, the prediction accuracy was 96.2% for the top ten ranking by stable score parameter learning; this accuracy is sufficient for a mathematical input interface system.
For the entire collection see [Zbl 1379.13001].
MSC:
97U70 Technological tools, calculators (aspects of mathematics education)
68T05 Learning and adaptive systems in artificial intelligence
68U35 Computing methodologies for information systems (hypertext navigation, interfaces, decision support, etc.)
Software:
STACK
PDF BibTeX XML Cite
Full Text: DOI
References:
[1] 1. Fukui, T.: An intelligent method of interactive user interface for digitalized mathematical expressions. RIMS Kokyuroku 1780 , 160-171 (2012) (in Japanese)
[2] 2. Fukui, T.: The performance of interactive user interface for digitalized mathematical expressions using an intelligent formatting from linear strings. RIMS Kokyuroku 1785 , 32-44 (2012). (in Japanese)
[3] 3. Fukui, T.: An intelligent user interface technology for easy formatting of digitalized mathematical expressions-a mathematical expression editor on web-browser. Interaction 2013 IPSJ symposium, No.1, 2EX13-50, pp. 537-540 (2013) (in Japanese)
[4] 4. Fukui, T.: Prediction for converting linear strings to mathematical formulae using machine learning. In: Proceedings of ARG WI2, No. 6, pp. 67-72 (2015) (in Japanese)
[5] 5. Garay-Vitoria, N., Abascal, J.: Text prediction systems: a survey. Univers. Access. Inf. Soc. 4 (3), 188-203 (2006)
[6] 6. Hijikata, Y., Horie, K., Nishida, S.: Predictive input interface of mathematical formulas Human-Computer Interaction-INTERACT2013, Vol. 8117 of the series Lecture Notes in Computer Science. Springer, New York (2013)
[7] 7. Hunnicutt, S.: Input and output alternative in word prediction. STL/QPRS 28 (2-3), 15-29 (1987)
[8] 8. Iidaka, S., Matsumoto, Y., et al.: Mathematics I, 001 , TOKYO SHOSEKI (2012) (in Japanese)
[9] 9. Manning, C.D., Scheutze, H.: Foundations of Statistical Natural Language Processing. The MIT Press, London (2012)
[10] 10. Pollanen, M., Wisniewski, T., Yu, X.: XPRESS: a novice interface for the real-time communication of mathematical expressions, In: Proceedings of MathUI (2007)
[11] 11. Sangwin, CJ.: Computer aided assessment of mathematics using STACK, In: Proceedings of ICME, vol. 12 (2012)
[12] 12. Shirai, S., Fukui, T.: Development and evaluation of a web-based drill system to master basic math formulae using a new interactive math input method, Mathematical Software—ICMS2014, vol. 8592 of the Series Lecture Notes in Computer Science, pp. 621-628. Springer, New York (2014) · Zbl 06341374
[13] 13. Shirai, S., Fukui, T.: Improvement in the input of mathematical formulae into STACK using interactive methodology. Comput. Educ. 37 , 85-90 (2014) (in Japanese)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.