Please use this identifier to cite or link to this item:
Title: Deep learning techniques for math word problems
Authors: Vu Duc Anh
Keywords: Computer and Information Science
Issue Date: 2024
Publisher: Nanyang Technological University
Source: Vu Duc Anh (2024). Deep learning techniques for math word problems. Final Year Project (FYP), Nanyang Technological University, Singapore.
Abstract: This paper presents a comprehensive investigation into Curriculum Learning (CL) applied to Math Word Problem (MWP) solving, examining its efficacy across a spectrum of scales and difficulty levels. Our study encompasses extensive experiments conducted on both small-scale and large-scale language models across three distinct MWP datasets, featuring problems of varying difficulty ranges. Through rigorous evaluation, we find that curriculum learning yield better performance than traditional training in MWP solving tasks. We also find the potential of anti-curriculum learning in solving hard mathematical questions. Additionally, we offer an in-depth analysis of the mechanisms and effects of curriculum learning and its variations in MWP solving
Schools: School of Computer Science and Engineering 
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
Vu_Duc_Anh_s_FYP (1).pdf
  Restricted Access
1.67 MBAdobe PDFView/Open

Page view(s)

Updated on Jul 23, 2024


Updated on Jul 23, 2024

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.