Show simple item record

dc.contributor.advisor Dias G
dc.contributor.advisor Ranathunga S
dc.contributor.author Fernando K
dc.date.accessioned 2019
dc.date.available 2019
dc.date.issued 2019
dc.identifier.uri http://dl.lib.mrt.ac.lk/handle/123/15815
dc.description.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. en_US
dc.language.iso en en_US
dc.subject COMPUTER SCIENCE AND ENGINEERING-Dissertations en_US
dc.subject MATHEMATICAL TECHNIQUES-Set Theory en_US
dc.subject MATH WORD PROBLEMS en_US
dc.title Automatic answer generation for math word problems en_US
dc.type Thesis-Abstract en_US
dc.identifier.faculty Engineering en_US
dc.identifier.degree MSc in Computer Science and Engineering by research en_US
dc.identifier.department Department of Computer Science & Engineering en_US
dc.date.accept 2019
dc.identifier.accno TH3870 en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record