Deep learning techniques for math word problems
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...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/178278 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-178278 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1782782024-06-14T15:37:42Z Deep learning techniques for math word problems Vu Duc Anh Luu Anh Tuan School of Computer Science and Engineering anhtuan.luu@ntu.edu.sg Computer and Information Science 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 Bachelor's degree 2024-06-11T12:33:45Z 2024-06-11T12:33:45Z 2024 Final Year Project (FYP) Vu Duc Anh (2024). Deep learning techniques for math word problems. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/178278 https://hdl.handle.net/10356/178278 en application/pdf Nanyang Technological University |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Computer and Information Science |
spellingShingle |
Computer and Information Science Vu Duc Anh Deep learning techniques for math word problems |
description |
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 |
author2 |
Luu Anh Tuan |
author_facet |
Luu Anh Tuan Vu Duc Anh |
format |
Final Year Project |
author |
Vu Duc Anh |
author_sort |
Vu Duc Anh |
title |
Deep learning techniques for math word problems |
title_short |
Deep learning techniques for math word problems |
title_full |
Deep learning techniques for math word problems |
title_fullStr |
Deep learning techniques for math word problems |
title_full_unstemmed |
Deep learning techniques for math word problems |
title_sort |
deep learning techniques for math word problems |
publisher |
Nanyang Technological University |
publishDate |
2024 |
url |
https://hdl.handle.net/10356/178278 |
_version_ |
1806059775028363264 |