Skip to main navigation Skip to search Skip to main content

Improving a Graph-to-Tree Model for Solving Math Word Problems

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In the area of Math Word Problem (MWP), various methods based on deep learning technology have been actively researched. Graph-to-Tree (Graph2Tree) is one of those methods which uses a graph-based encoder and a tree-based decoder to understand the word problem and to generate a valid equation. This method is proven to be well-performed by achieving state-of-the-art on several benchmarks. However, on the benchmark of SVAMP, recent methods including Sequence-to-Sequence (Seq2Seq), Goal-driven Tree-Structured MWP Solver (GTS), and Graph2Tree performs poorly, unable to cope with several variation types that requires natural language comprehension capability. In this paper, we propose an improved version of Graph2Tree which considers the characteristics of natural language to understand the word problems. On top of the original Graph2Tree model, we additionally build Dependency Graph and enhance the Quantity Cell Graph to Softly Expanded Quantity Cell Graph. This helps a graph-based encoder to capture the relationship among words. Also, we introduce question embedding for the tree-based decoder to generate equation based on the question given as input. We conduct experiments to evaluate our model against the original Graph2Tree model on three available datasets: MAWPS, ASDiv-A, and SVAMP. We also present case studies to qualitatively examine the effectiveness of the methods and showed that our methods have improved the original Graph2Tree model.

Original languageEnglish
Title of host publicationProceedings of the 2022 16th International Conference on Ubiquitous Information Management and Communication, IMCOM 2022
EditorsSukhan Lee, Hyunseung Choo, Roslan Ismail
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665426787
DOIs
StatePublished - 2022
Event16th International Conference on Ubiquitous Information Management and Communication, IMCOM 2022 - Seoul, Korea, Republic of
Duration: 3 Jan 20225 Jan 2022

Publication series

NameProceedings of the 2022 16th International Conference on Ubiquitous Information Management and Communication, IMCOM 2022

Conference

Conference16th International Conference on Ubiquitous Information Management and Communication, IMCOM 2022
Country/TerritoryKorea, Republic of
CitySeoul
Period3/01/225/01/22

Fingerprint

Dive into the research topics of 'Improving a Graph-to-Tree Model for Solving Math Word Problems'. Together they form a unique fingerprint.

Cite this