MathGraph: A Knowledge Graph for Automatically Solving Mathematical Exercises

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, the design of MathGraph has major differences from existing knowledge graphs. 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.

[1]  Yinghui Wu,et al.  Fact Checking in Knowledge Graphs with Ontological Subgraph Patterns , 2018, Data Science and Engineering.

[2]  Roberto Baldoni,et al.  A Survey of Symbolic Execution Techniques , 2016, ACM Comput. Surv..

[3]  Tomoko Kojiri,et al.  Automatic Generation of Answers Using Solution Network for Mathematical Exercises , 2005, KES.

[4]  M. Ganesalingam,et al.  A Fully Automatic Theorem Prover with Human-Style Output , 2016, Journal of Automated Reasoning.

[5]  R. Fletcher,et al.  Filter-type Algorithms for Solving Systems of Algebraic Equations and Inequalities , 2003 .

[6]  Boris Polyak.  Gradient methods for solving equations and inequalities , 1964 .

[7]  Andy R. Terrel,et al.  SymPy: Symbolic computing in Python , 2017, PeerJ Prepr..

[8]  Richard Chbeir,et al.  RDF-F: RDF Datatype inFerring Framework , 2018, Data Science and Engineering.

[9]  Lei Zou,et al.  Question Answering Over Knowledge Graphs: Question Understanding Via Template Decomposition , 2018, Proc. VLDB Endow..

[10]  Le Song,et al.  Variational Reasoning for Question Answering with Knowledge Graph , 2017, AAAI.

[11]  José Paulo Leal,et al.  A CLP-Based Tool for Computer Aided Generation and Solving of Maths Exercises , 2003, PADL.

[12]  Estevam R. Hruschka,et al.  Toward an Architecture for Never-Ending Language Learning , 2010, AAAI.

[13]  James C. King,et al.  Symbolic execution and program testing , 1976, CACM.

[14]  Patrick Cousot,et al.  Abstract interpretation: a unified lattice model for static analysis of programs by construction or approximation of fixpoints , 1977, POPL.

[15]  Hoifung Poon,et al.  Compositional Learning of Embeddings for Relation Paths in Knowledge Base and Text , 2016, ACL.

[16]  John Miller,et al.  Traversing Knowledge Graphs in Vector Space , 2015, EMNLP.

[17]  Guoliang Li,et al.  Approximate Query Processing: What is New and Where to Go? , 2018, Data Science and Engineering.