Automatic answer generation for math word problems

Abstract

A math word problem (MWP) is a mathematical problem expressed using natural language. In this research, elementary level set-related word problems in which information is given in set notation are considered. As per our knowledge, this is the first research addressing set theory related word problems. This research introduces an abstract representation to interpret mathematical semantics of set expressions and relations between sets. Two methods to extract given set related expressions were implemented: rule based method and a statistical method. Results show that statistical method is more robust to typing errors and unexpected expression formats. A parser based on a context free grammar is introduced to validate set related expressions and give feedback to the user when there are incorrect expressions. Along with these functionalities, we present a complete set problem solver system that understand and solve a given set word problem. In addition to the solver, we experiment in extracting mathematical expressions from unstructured plain text using sequential classifiers. Several sequential classification models including conditional random-fields (CRF) and Long-Short Term Memory (LSTM) networks were compared with word and character level features. The results show that using character level features significantly increase the performance of mathematical expression extraction.