Towards Automatic Mathematical Exercise Solving

Knowledge graphs are widely applied in many applications. Automatically solving mathematical exercises is also an interesting task which can be enhanced by knowledge reasoning. In this paper, we design MathGraph, a knowledge graph aiming to solve high school mathematical exercises. Since it requires...

Full description

Saved in:
Bibliographic Details
Published in:Data science and engineering 2019-09, Vol.4 (3), p.179-192
Main Authors: Zhao, Tianyu, Chai, Chengliang, Luo, Yuyu, Feng, Jianhua, Huang, Yan, Yang, Songfan, Yuan, Haitao, Li, Haoda, Li, Kaiyu, Zhu, Fu, Pan, Kang
Format: Article
Language:English
Subjects:
Algorithm Analysis and Problem Complexity
Algorithms
Artificial Intelligence
Chemistry and Earth Sciences
Computer Science
Crowdsourcing
Data Mining and Knowledge Discovery
Database Management
Knowledge graph
Knowledge reasoning
Mathematical analysis
Mathematical exercise
Physics
Statistics for Engineering
Systems and Data Security
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Knowledge graphs are widely applied in many applications. Automatically solving mathematical exercises is also an interesting task which can be enhanced by knowledge reasoning. In this paper, we design MathGraph, a knowledge graph aiming to solve high school mathematical exercises. Since it requires fine-grained mathematical derivation and calculation of different mathematical objects, we design a crowdsourcing-based method to help build MathGraph. MathGraph supports massive kinds of mathematical objects, operations and constraints which may be involved in exercises. Furthermore, we propose an algorithm to align a semantically parsed exercise to MathGraph and figure out the answer automatically. Extensive experiments on real-world datasets verify the effectiveness of MathGraph.
ISSN:2364-1185
2364-1541
DOI:10.1007/s41019-019-00098-w