CoSPLADE: Contextualizing SPLADE for Conversational Information Retrieval - Archive ouverte HAL Access content directly
Conference Papers Year : 2023

CoSPLADE: Contextualizing SPLADE for Conversational Information Retrieval

Abstract

Conversational search is a difficult task as it aims at retrieving documents based not only on the current user query but also on the full conversation history. Most of the previous methods have focused on a multi-stage ranking approach relying on query reformulation, a critical intermediate step that might lead to a sub-optimal retrieval. Other approaches have tried to use a fully neural IR first-stage, but are either zero-shot or rely on full learning-to-rank based on a dataset with pseudo-labels. In this work, leveraging the CANARD dataset, we propose an innovative lightweight learning technique to train a first-stage ranker based on SPLADE. By relying on SPLADE sparse representations, we show that, when combined with a second-stage ranker based on T5Mono, the results are competitive on the TREC
Fichier principal
Vignette du fichier
ECIR_2023___coSPLADE.pdf (456.82 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04168526 , version 1 (21-07-2023)

Licence

Identifiers

Cite

Nam Le Hai, Thomas Gerald, Thibault Formal, Jian-Yun Nie, Benjamin Piwowarski, et al.. CoSPLADE: Contextualizing SPLADE for Conversational Information Retrieval. 45th European Conference on Information Retrieval (ECIR 2023), Apr 2023, Dublin, Ireland. pp.537-552, ⟨10.1007/978-3-031-28244-7_34⟩. ⟨hal-04168526⟩
32 View
87 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More