Understanding explicit arithmetic word problems and explicit plane geometry problems using syntax-semantics models

This paper presents two algorithms for understanding explicit arithmetic word problems (EAWPs) and explicit plane geometry problems (EPGPs) following the sharing approach, respectively. This approach proposed in this paper models understanding math problems as a problem of relation extraction, instead of as the problem of understanding the semantics of natural language. Then it further proposes a syntax-semantics (S2) model method to extract math relations. The S2 model method is very effective in that only 116 models can extract most of relations in EAWPs and that only 48 models can extract most of relations in EPGP texts. The experimental results show that the proposed algorithms can understand EAWPs and EPGPs very well.