Improving conversational recommender system via contextual and time-aware modeling with less domain-specific knowledge

Conversational Recommender Systems (CRS) has become an emerging research topic seeking to perform recommendations through interactive conversations, which generally consist of generation and recommendation modules. Prior work on CRS tends to incorporate more external and domain-specific knowledge li...

Full description

Saved in:
Bibliographic Details
Main Authors: WANG, Lingzhi, JOTY, Shafiq, GAO, Wei, ZENG, Xingshan, WONG, Kam-Fai
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2024
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/8778
https://ink.library.smu.edu.sg/context/sis_research/article/9781/viewcontent/ImproConversationRecommenderSys_av.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-9781
record_format dspace
spelling sg-smu-ink.sis_research-97812024-05-30T08:59:54Z Improving conversational recommender system via contextual and time-aware modeling with less domain-specific knowledge WANG, Lingzhi JOTY, Shafiq GAO, Wei ZENG, Xingshan WONG, Kam-Fai Conversational Recommender Systems (CRS) has become an emerging research topic seeking to perform recommendations through interactive conversations, which generally consist of generation and recommendation modules. Prior work on CRS tends to incorporate more external and domain-specific knowledge like item reviews to enhance performance. Despite the fact that the collection and annotation of the external domain-specific information needs much human effort and degenerates the generalizability, too much extra knowledge introduces more difficulty to balance among them. Therefore, we propose to fully discover and extract the internal knowledge from the context. We capture both entity-level and contextual-level representations to jointly model user preferences for the recommendation, where a time-aware attention is designed to emphasize the recently appeared items in entity-level representations. We further use the pre-trained BART to initialize the generation module to alleviate the data scarcity and enhance the context modeling. In addition to conducting experiments on a popular dataset (ReDial), we also include a multi-domain dataset (OpenDialKG) to show the effectiveness of our model. Experiments on both datasets show that our model achieves better performance on most evaluation metrics with less external knowledge and generalizes well to other domains. Additional analyses on the recommendation and generation tasks demonstrate the effectiveness of our model in different scenarios. 2024-02-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8778 info:doi/10.1109/TKDE.2024.3397321 https://ink.library.smu.edu.sg/context/sis_research/article/9781/viewcontent/ImproConversationRecommenderSys_av.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Recommender System Conversational Recommendation Pre-trained Language Model Databases and Information Systems Numerical Analysis and Scientific Computing
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Recommender System
Conversational Recommendation
Pre-trained Language Model
Databases and Information Systems
Numerical Analysis and Scientific Computing
spellingShingle Recommender System
Conversational Recommendation
Pre-trained Language Model
Databases and Information Systems
Numerical Analysis and Scientific Computing
WANG, Lingzhi
JOTY, Shafiq
GAO, Wei
ZENG, Xingshan
WONG, Kam-Fai
Improving conversational recommender system via contextual and time-aware modeling with less domain-specific knowledge
description Conversational Recommender Systems (CRS) has become an emerging research topic seeking to perform recommendations through interactive conversations, which generally consist of generation and recommendation modules. Prior work on CRS tends to incorporate more external and domain-specific knowledge like item reviews to enhance performance. Despite the fact that the collection and annotation of the external domain-specific information needs much human effort and degenerates the generalizability, too much extra knowledge introduces more difficulty to balance among them. Therefore, we propose to fully discover and extract the internal knowledge from the context. We capture both entity-level and contextual-level representations to jointly model user preferences for the recommendation, where a time-aware attention is designed to emphasize the recently appeared items in entity-level representations. We further use the pre-trained BART to initialize the generation module to alleviate the data scarcity and enhance the context modeling. In addition to conducting experiments on a popular dataset (ReDial), we also include a multi-domain dataset (OpenDialKG) to show the effectiveness of our model. Experiments on both datasets show that our model achieves better performance on most evaluation metrics with less external knowledge and generalizes well to other domains. Additional analyses on the recommendation and generation tasks demonstrate the effectiveness of our model in different scenarios.
format text
author WANG, Lingzhi
JOTY, Shafiq
GAO, Wei
ZENG, Xingshan
WONG, Kam-Fai
author_facet WANG, Lingzhi
JOTY, Shafiq
GAO, Wei
ZENG, Xingshan
WONG, Kam-Fai
author_sort WANG, Lingzhi
title Improving conversational recommender system via contextual and time-aware modeling with less domain-specific knowledge
title_short Improving conversational recommender system via contextual and time-aware modeling with less domain-specific knowledge
title_full Improving conversational recommender system via contextual and time-aware modeling with less domain-specific knowledge
title_fullStr Improving conversational recommender system via contextual and time-aware modeling with less domain-specific knowledge
title_full_unstemmed Improving conversational recommender system via contextual and time-aware modeling with less domain-specific knowledge
title_sort improving conversational recommender system via contextual and time-aware modeling with less domain-specific knowledge
publisher Institutional Knowledge at Singapore Management University
publishDate 2024
url https://ink.library.smu.edu.sg/sis_research/8778
https://ink.library.smu.edu.sg/context/sis_research/article/9781/viewcontent/ImproConversationRecommenderSys_av.pdf
_version_ 1814047526616039424