Multi modal personalized explanation generation
In the domain of recommendation systems, personalized explainable recommendation systems are gaining significant attention. This dissertation contributes to this field by compiling publicly available real-world image data for the TripAdvisor dataset. Furthermore, a method has been developed and tes...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Thesis-Master by Coursework |
Language: | English |
Published: |
Nanyang Technological University
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/175910 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-175910 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1759102024-05-10T15:49:47Z Multi modal personalized explanation generation Marantika, Winda Kirana Alex Chichung Kot School of Electrical and Electronic Engineering EACKOT@ntu.edu.sg Computer and Information Science Engineering Recommender NLP VQVAE Personalized explanation Transformer In the domain of recommendation systems, personalized explainable recommendation systems are gaining significant attention. This dissertation contributes to this field by compiling publicly available real-world image data for the TripAdvisor dataset. Furthermore, a method has been developed and tested that generates these recommendations by incorporating image data, user ID, item ID, user persona, and item persona. The image feature data is derived from a quantized vector encoder from VQVAE. We have devised and tested a method capable of generating personalized explainable recommendations by incorporating image data as input. The visual token is extracted from the output of a quantized vector encoder from VQVAE. This data is combined with the user ID, item ID, user persona, and item persona to generate personalized explanations through a lightweight encoder-decoder transformer. The evaluation concludes that our model can generate superior text explainability, diversity, and quality on two publicly available datasets if no feature word is incorporated in the training or evaluation process. The addition of an image feature can enhance the model’s ability to generate better text quality. Master's degree 2024-05-09T02:10:11Z 2024-05-09T02:10:11Z 2024 Thesis-Master by Coursework Marantika, W. K. (2024). Multi modal personalized explanation generation. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/175910 https://hdl.handle.net/10356/175910 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 Engineering Recommender NLP VQVAE Personalized explanation Transformer |
spellingShingle |
Computer and Information Science Engineering Recommender NLP VQVAE Personalized explanation Transformer Marantika, Winda Kirana Multi modal personalized explanation generation |
description |
In the domain of recommendation systems, personalized explainable recommendation systems are gaining significant attention. This dissertation contributes to this field by compiling publicly available real-world image data for the TripAdvisor dataset.
Furthermore, a method has been developed and tested that generates these recommendations by incorporating image data, user ID, item ID, user persona, and item persona. The image feature data is derived from a quantized vector encoder from VQVAE.
We have devised and tested a method capable of generating personalized explainable recommendations by incorporating image data as input. The visual
token is extracted from the output of a quantized vector encoder from VQVAE.
This data is combined with the user ID, item ID, user persona, and item persona
to generate personalized explanations through a lightweight encoder-decoder
transformer.
The evaluation concludes that our model can generate superior text explainability,
diversity, and quality on two publicly available datasets if no feature word
is incorporated in the training or evaluation process. The addition of an image
feature can enhance the model’s ability to generate better text quality. |
author2 |
Alex Chichung Kot |
author_facet |
Alex Chichung Kot Marantika, Winda Kirana |
format |
Thesis-Master by Coursework |
author |
Marantika, Winda Kirana |
author_sort |
Marantika, Winda Kirana |
title |
Multi modal personalized explanation generation |
title_short |
Multi modal personalized explanation generation |
title_full |
Multi modal personalized explanation generation |
title_fullStr |
Multi modal personalized explanation generation |
title_full_unstemmed |
Multi modal personalized explanation generation |
title_sort |
multi modal personalized explanation generation |
publisher |
Nanyang Technological University |
publishDate |
2024 |
url |
https://hdl.handle.net/10356/175910 |
_version_ |
1814047276515983360 |