RALI@TREC iKAT 2024: Achieving Personalization via Retrieval Fusion in Conversational Search

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hui, Yuchen, Mo, Fengran, Mao, Milan, Nie, Jian-Yun
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909424466001920
author Hui, Yuchen
Mo, Fengran
Mao, Milan
Nie, Jian-Yun
author_facet Hui, Yuchen
Mo, Fengran
Mao, Milan
Nie, Jian-Yun
contents The Recherche Appliquee en Linguistique Informatique (RALI) team participated in the 2024 TREC Interactive Knowledge Assistance (iKAT) Track. In personalized conversational search, effectively capturing a user's complex search intent requires incorporating both contextual information and key elements from the user profile into query reformulation. The user profile often contains many relevant pieces, and each could potentially complement the user's information needs. It is difficult to disregard any of them, whereas introducing an excessive number of these pieces risks drifting from the original query and hinders search performance. This is a challenge we denote as over-personalization. To address this, we propose different strategies by fusing ranking lists generated from the queries with different levels of personalization.
format Preprint
id arxiv_https___arxiv_org_abs_2412_07998
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RALI@TREC iKAT 2024: Achieving Personalization via Retrieval Fusion in Conversational Search
Hui, Yuchen
Mo, Fengran
Mao, Milan
Nie, Jian-Yun
Information Retrieval
The Recherche Appliquee en Linguistique Informatique (RALI) team participated in the 2024 TREC Interactive Knowledge Assistance (iKAT) Track. In personalized conversational search, effectively capturing a user's complex search intent requires incorporating both contextual information and key elements from the user profile into query reformulation. The user profile often contains many relevant pieces, and each could potentially complement the user's information needs. It is difficult to disregard any of them, whereas introducing an excessive number of these pieces risks drifting from the original query and hinders search performance. This is a challenge we denote as over-personalization. To address this, we propose different strategies by fusing ranking lists generated from the queries with different levels of personalization.
title RALI@TREC iKAT 2024: Achieving Personalization via Retrieval Fusion in Conversational Search
topic Information Retrieval
url https://arxiv.org/abs/2412.07998