Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/178278
Full metadata record
DC FieldValueLanguage
dc.contributor.authorVu Duc Anhen_US
dc.date.accessioned2024-06-11T12:33:45Z-
dc.date.available2024-06-11T12:33:45Z-
dc.date.issued2024-
dc.identifier.citationVu Duc Anh (2024). Deep learning techniques for math word problems. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/178278en_US
dc.identifier.urihttps://hdl.handle.net/10356/178278-
dc.description.abstractThis 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 solvingen_US
dc.language.isoenen_US
dc.publisherNanyang Technological Universityen_US
dc.subjectComputer and Information Scienceen_US
dc.titleDeep learning techniques for math word problemsen_US
dc.typeFinal Year Project (FYP)en_US
dc.contributor.supervisorLuu Anh Tuanen_US
dc.contributor.schoolSchool of Computer Science and Engineeringen_US
dc.description.degreeBachelor's degreeen_US
dc.contributor.supervisoremailanhtuan.luu@ntu.edu.sgen_US
item.fulltextWith Fulltext-
item.grantfulltextrestricted-
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)

42
Updated on Jul 18, 2024

Download(s)

4
Updated on Jul 18, 2024

Google ScholarTM

Check

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