Resources for brewing beir: Reproducible reference models and statistical analyses

E Kamalloo, N Thakur, C Lassance, X Ma… - Proceedings of the 47th …, 2024 - dl.acm.org
BEIR is a benchmark dataset originally designed for zero-shot evaluation of retrieval models
across 18 different domain/task combinations. In recent years, we have witnessed the …

Splate: Sparse late interaction retrieval

T Formal, S Clinchant, H Déjean… - Proceedings of the 47th …, 2024 - dl.acm.org
The late interaction paradigm introduced with ColBERT stands out in the neural Information
Retrieval space, offering a compelling effectiveness-efficiency trade-off across many …

Two-Step SPLADE: Simple, Efficient and Effective Approximation of SPLADE

C Lassance, H Dejean, S Clinchant… - European Conference on …, 2024 - Springer
Learned sparse models such as SPLADE have successfully shown how to incorporate the
benefits of state-of-the-art neural information retrieval models into the classical inverted …

[PDF][PDF] Exploring Effect-Size-Based Meta-Analysis for Multi-Dataset Evaluation.

M Sertkan, S Althammer, S Hofstätter, P Knees… - Perspectives …, 2023 - ceur-ws.org
In this paper, we address the essential yet complex task of evaluating Recommender
Systems (RecSys) across multiple datasets. This is critical for gauging their overall …