Snippet-based Conversational Recommender System

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Haibo, Otani, Naoki, Kim, Hannah, Zhang, Dan, Bhutani, Nikita
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913793938817024
author Sun, Haibo
Otani, Naoki
Kim, Hannah
Zhang, Dan
Bhutani, Nikita
author_facet Sun, Haibo
Otani, Naoki
Kim, Hannah
Zhang, Dan
Bhutani, Nikita
contents Conversational Recommender Systems (CRS) engage users in interactive dialogues to gather preferences and provide personalized recommendations. While existing studies have advanced conversational strategies, they often rely on predefined attributes or expensive, domain-specific annotated datasets, which limits their flexibility in handling diverse user preferences and adaptability across domains. We propose SnipRec, a novel resource-efficient approach that leverages user-generated content, such as customer reviews, to capture a broader range of user expressions. By employing large language models to map reviews and user responses into concise snippets, SnipRec represents user preferences and retrieves relevant items without the need for intensive manual data collection or fine-tuning. Experiments across the restaurant, book, and clothing domains show that snippet-based representations outperform document- and sentence-based representations, achieving Hits@10 of 0.25-0.55 with 3,000 to 10,000 candidate items while successfully handling free-form user responses.
format Preprint
id arxiv_https___arxiv_org_abs_2411_06064
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Snippet-based Conversational Recommender System
Sun, Haibo
Otani, Naoki
Kim, Hannah
Zhang, Dan
Bhutani, Nikita
Information Retrieval
Conversational Recommender Systems (CRS) engage users in interactive dialogues to gather preferences and provide personalized recommendations. While existing studies have advanced conversational strategies, they often rely on predefined attributes or expensive, domain-specific annotated datasets, which limits their flexibility in handling diverse user preferences and adaptability across domains. We propose SnipRec, a novel resource-efficient approach that leverages user-generated content, such as customer reviews, to capture a broader range of user expressions. By employing large language models to map reviews and user responses into concise snippets, SnipRec represents user preferences and retrieves relevant items without the need for intensive manual data collection or fine-tuning. Experiments across the restaurant, book, and clothing domains show that snippet-based representations outperform document- and sentence-based representations, achieving Hits@10 of 0.25-0.55 with 3,000 to 10,000 candidate items while successfully handling free-form user responses.
title Snippet-based Conversational Recommender System
topic Information Retrieval
url https://arxiv.org/abs/2411.06064