Efficient Conversational Search via Topical Locality in Dense Retrieval

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Muntean, Cristina Ioana, Nardini, Franco Maria, Perego, Raffaele, Rocchietti, Guido, Rulli, Cosimo
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913813070086144
author Muntean, Cristina Ioana
Nardini, Franco Maria
Perego, Raffaele
Rocchietti, Guido
Rulli, Cosimo
author_facet Muntean, Cristina Ioana
Nardini, Franco Maria
Perego, Raffaele
Rocchietti, Guido
Rulli, Cosimo
contents Pre-trained language models have been widely exploited to learn dense representations of documents and queries for information retrieval. While previous efforts have primarily focused on improving effectiveness and user satisfaction, response time remains a critical bottleneck of conversational search systems. To address this, we exploit the topical locality inherent in conversational queries, i.e., the tendency of queries within a conversation to focus on related topics. By leveraging query embedding similarities, we dynamically restrict the search space to semantically relevant document clusters, reducing computational complexity without compromising retrieval quality. We evaluate our approach on the TREC CAsT 2019 and 2020 datasets using multiple embedding models and vector indexes, achieving improvements in processing speed of up to 10.4X with little loss in performance (4.4X without any loss). Our results show that the proposed system effectively handles complex, multiturn queries with high precision and efficiency, offering a practical solution for real-time conversational search.
format Preprint
id arxiv_https___arxiv_org_abs_2504_21507
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient Conversational Search via Topical Locality in Dense Retrieval
Muntean, Cristina Ioana
Nardini, Franco Maria
Perego, Raffaele
Rocchietti, Guido
Rulli, Cosimo
Information Retrieval
Human-Computer Interaction
H.3
Pre-trained language models have been widely exploited to learn dense representations of documents and queries for information retrieval. While previous efforts have primarily focused on improving effectiveness and user satisfaction, response time remains a critical bottleneck of conversational search systems. To address this, we exploit the topical locality inherent in conversational queries, i.e., the tendency of queries within a conversation to focus on related topics. By leveraging query embedding similarities, we dynamically restrict the search space to semantically relevant document clusters, reducing computational complexity without compromising retrieval quality. We evaluate our approach on the TREC CAsT 2019 and 2020 datasets using multiple embedding models and vector indexes, achieving improvements in processing speed of up to 10.4X with little loss in performance (4.4X without any loss). Our results show that the proposed system effectively handles complex, multiturn queries with high precision and efficiency, offering a practical solution for real-time conversational search.
title Efficient Conversational Search via Topical Locality in Dense Retrieval
topic Information Retrieval
Human-Computer Interaction
H.3
url https://arxiv.org/abs/2504.21507