72 citations · 148 across the 43 of their papers we have counts for
5 papers · 1 filter
An Efficiency Study for SPLADE Models
Carlos Lassance, Stéphane Clinchant
Latency and efficiency issues are often overlooked when evaluating IR models based on Pretrained Language Models (PLMs) in reason of multiple hardware and software testing scenario…
From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective
Thibault Formal, Carlos Lassance, Benjamin Piwowarski +1
Neural retrievers based on dense representations combined with Approximate Nearest Neighbors search have recently received a lot of attention, owing their success to distillation a…
LayoutXLM vs. GNN: An Empirical Evaluation of Relation Extraction for Documents
Hervé Déjean, Stéphane Clinchant, Jean-Luc Meunier
This paper investigates the Relation Extraction task in documents by benchmarking two different neural network models: a multi-modal language model (LayoutXLM) and a Graph Neural N…
MS-Shift: An Analysis of MS MARCO Distribution Shifts on Neural Retrieval
Simon Lupart, Thibault Formal, Stéphane Clinchant
Pre-trained Language Models have recently emerged in Information Retrieval as providing the backbone of a new generation of neural systems that outperform traditional methods on a…
Composite Code Sparse Autoencoders for first stage retrieval
Carlos Lassance, Thibault Formal, Stephane Clinchant
We propose a Composite Code Sparse Autoencoder (CCSA) approach for Approximate Nearest Neighbor (ANN) search of document representations based on Siamese-BERT models. In Informatio…