Leveraging knowledge graph embedding for effective conversational recommendation

Conversational recommender system (CRS), which combines the techniques of dialogue system and recommender system, has obtained increasing interest recently. In contrast to the traditional recommender system, it learns the user preference better through interactions (i.e. conversations), and then fur...

Full description

Saved in:
Bibliographic Details
Main Author: Xia, Yunwen
Other Authors: Zhang Jie
Format: Thesis-Master by Research
Language:English
Published: Nanyang Technological University 2022
Subjects:
Online Access:https://hdl.handle.net/10356/155658
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-155658
record_format dspace
spelling sg-ntu-dr.10356-1556582022-04-04T03:16:53Z Leveraging knowledge graph embedding for effective conversational recommendation Xia, Yunwen Zhang Jie School of Computer Science and Engineering ZhangJ@ntu.edu.sg Engineering::Computer science and engineering Conversational recommender system (CRS), which combines the techniques of dialogue system and recommender system, has obtained increasing interest recently. In contrast to the traditional recommender system, it learns the user preference better through interactions (i.e. conversations), and then further boosts the recommendation performance. However, existing studies on CRS ignore to address the relationship among attributes, users, and items effectively, which might lead to inappropriate questions and inaccurate recommendations. In this view, we propose a knowledge graph (KG)-based conversational recommender system (referred to as KG-CRS). Specifically, we first integrate the user-item graph and item-attribute graph into a dynamic graph, i.e., dynamically changing during the dialogue process by removing negative items or attributes. We then learn the informative embedding of users, items, and attributes by also considering propagation through neighbors on the graph. Extensive experiments on three real datasets validate the superiority of our method in terms of both the recommendation and conversation tasks. Master of Engineering 2022-03-10T04:34:36Z 2022-03-10T04:34:36Z 2022 Thesis-Master by Research Xia, Y. (2022). Leveraging knowledge graph embedding for effective conversational recommendation. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/155658 https://hdl.handle.net/10356/155658 10.32657/10356/155658 en This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0). 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 Engineering::Computer science and engineering
spellingShingle Engineering::Computer science and engineering
Xia, Yunwen
Leveraging knowledge graph embedding for effective conversational recommendation
description Conversational recommender system (CRS), which combines the techniques of dialogue system and recommender system, has obtained increasing interest recently. In contrast to the traditional recommender system, it learns the user preference better through interactions (i.e. conversations), and then further boosts the recommendation performance. However, existing studies on CRS ignore to address the relationship among attributes, users, and items effectively, which might lead to inappropriate questions and inaccurate recommendations. In this view, we propose a knowledge graph (KG)-based conversational recommender system (referred to as KG-CRS). Specifically, we first integrate the user-item graph and item-attribute graph into a dynamic graph, i.e., dynamically changing during the dialogue process by removing negative items or attributes. We then learn the informative embedding of users, items, and attributes by also considering propagation through neighbors on the graph. Extensive experiments on three real datasets validate the superiority of our method in terms of both the recommendation and conversation tasks.
author2 Zhang Jie
author_facet Zhang Jie
Xia, Yunwen
format Thesis-Master by Research
author Xia, Yunwen
author_sort Xia, Yunwen
title Leveraging knowledge graph embedding for effective conversational recommendation
title_short Leveraging knowledge graph embedding for effective conversational recommendation
title_full Leveraging knowledge graph embedding for effective conversational recommendation
title_fullStr Leveraging knowledge graph embedding for effective conversational recommendation
title_full_unstemmed Leveraging knowledge graph embedding for effective conversational recommendation
title_sort leveraging knowledge graph embedding for effective conversational recommendation
publisher Nanyang Technological University
publishDate 2022
url https://hdl.handle.net/10356/155658
_version_ 1729789501304209408