Search Results for author: Stéphane Clinchant

Found 26 papers, 9 papers with code

A Thorough Comparison of Cross-Encoders and LLMs for Reranking SPLADE

no code implementations15 Mar 2024 Hervé Déjean, Stéphane Clinchant, Thibault Formal

We present a comparative study between cross-encoder and LLMs rerankers in the context of re-ranking effective SPLADE retrievers.

Re-Ranking

SPLADE-v3: New baselines for SPLADE

no code implementations11 Mar 2024 Carlos Lassance, Hervé Déjean, Thibault Formal, Stéphane Clinchant

A companion to the release of the latest version of the SPLADE library.

Benchmarking Middle-Trained Language Models for Neural Search

1 code implementation5 Jun 2023 Hervé Déjean, Stéphane Clinchant, Carlos Lassance, Simon Lupart, Thibault Formal

We compare both dense and sparse approaches under various finetuning protocols and middle training on different collections (MS MARCO, Wikipedia or Tripclick).

Benchmarking Language Modelling +1

A Static Pruning Study on Sparse Neural Retrievers

no code implementations25 Apr 2023 Carlos Lassance, Simon Lupart, Hervé Dejean, Stéphane Clinchant, Nicola Tonellotto

Sparse neural retrievers, such as DeepImpact, uniCOIL and SPLADE, have been introduced recently as an efficient and effective way to perform retrieval with inverted indexes.

Document Ranking Retrieval

The tale of two MS MARCO -- and their unfair comparisons

no code implementations25 Apr 2023 Carlos Lassance, Stéphane Clinchant

This is why this paper aims to report the importance of this issue so that researchers can be made aware of this problem and appropriately report their results.

Retrieval Vocal Bursts Valence Prediction

Parameter-Efficient Sparse Retrievers and Rerankers using Adapters

1 code implementation23 Mar 2023 Vaishali Pal, Carlos Lassance, Hervé Déjean, Stéphane Clinchant

While previous studies have only experimented with dense retriever or in a cross lingual retrieval scenario, in this paper we aim to complete the picture on the use of adapters in IR.

Domain Adaptation Information Retrieval +3

Naver Labs Europe (SPLADE) @ TREC NeuCLIR 2022

no code implementations10 Mar 2023 Carlos Lassance, Stéphane Clinchant

This paper describes our participation in the 2022 TREC NeuCLIR challenge.

Retrieval Translation

Naver Labs Europe (SPLADE) @ TREC Deep Learning 2022

no code implementations24 Feb 2023 Carlos Lassance, Stéphane Clinchant

This paper describes our participation to the 2022 TREC Deep Learning challenge.

Retrieval

Query Performance Prediction for Neural IR: Are We There Yet?

1 code implementation20 Feb 2023 Guglielmo Faggioli, Thibault Formal, Stefano Marchesin, Stéphane Clinchant, Nicola Ferro, Benjamin Piwowarski

On top of that, in lexical-oriented scenarios, QPPs fail to predict performance for neural IR systems on those queries where they differ from traditional approaches the most.

Passage Retrieval Retrieval

A Study on FGSM Adversarial Training for Neural Retrieval

no code implementations25 Jan 2023 Simon Lupart, Stéphane Clinchant

Neural retrieval models have acquired significant effectiveness gains over the last few years compared to term-based methods.

Data Augmentation Retrieval

An Efficiency Study for SPLADE Models

1 code implementation8 Jul 2022 Carlos Lassance, Stéphane Clinchant

SPLADE efficiency can be controlled via a regularization factor, but solely controlling this regularization has been shown to not be efficient enough.

Retrieval

From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective

1 code implementation10 May 2022 Thibault Formal, Carlos Lassance, Benjamin Piwowarski, Stéphane Clinchant

Neural retrievers based on dense representations combined with Approximate Nearest Neighbors search have recently received a lot of attention, owing their success to distillation and/or better sampling of examples for training -- while still relying on the same backbone architecture.

Language Modelling Representation Learning

LayoutXLM vs. GNN: An Empirical Evaluation of Relation Extraction for Documents

no code implementations9 May 2022 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 Network: Edge Convolution Network (ECN).

Benchmarking Language Modelling +2

MS-Shift: An Analysis of MS MARCO Distribution Shifts on Neural Retrieval

1 code implementation5 May 2022 Simon Lupart, Thibault Formal, Stéphane Clinchant

To this end, we build three query-based distribution shifts within MS MARCO (query-semantic, query-intent, query-length), which are used to evaluate the three main families of neural retrievers based on BERT: sparse, dense, and late-interaction -- as well as a monoBERT re-ranker.

Information Retrieval Retrieval

A Study on Token Pruning for ColBERT

no code implementations13 Dec 2021 Carlos Lassance, Maroua Maachou, Joohee Park, Stéphane Clinchant

Our experiments show that ColBERT indexes can be pruned up to 30\% on the MS MARCO passage collection without a significant drop in performance.

Match Your Words! A Study of Lexical Matching in Neural Information Retrieval

no code implementations10 Dec 2021 Thibault Formal, Benjamin Piwowarski, Stéphane Clinchant

Neural Information Retrieval models hold the promise to replace lexical matching models, e. g. BM25, in modern search engines.

Information Retrieval Retrieval

SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval

1 code implementation21 Sep 2021 Thibault Formal, Carlos Lassance, Benjamin Piwowarski, Stéphane Clinchant

Meanwhile, there has been a growing interest in learning \emph{sparse} representations for documents and queries, that could inherit from the desirable properties of bag-of-words models such as the exact matching of terms and the efficiency of inverted indexes.

Information Retrieval Retrieval +1

Masked Adversarial Generation for Neural Machine Translation

no code implementations1 Sep 2021 Badr Youbi Idrissi, Stéphane Clinchant

Attacking Neural Machine Translation models is an inherently combinatorial task on discrete sequences, solved with approximate heuristics.

Language Modelling Machine Translation +1

SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking

1 code implementation12 Jul 2021 Thibault Formal, Benjamin Piwowarski, Stéphane Clinchant

In neural Information Retrieval, ongoing research is directed towards improving the first retriever in ranking pipelines.

Information Retrieval Open-Domain Question Answering +1

A White Box Analysis of ColBERT

no code implementations17 Dec 2020 Thibault Formal, Benjamin Piwowarski, Stéphane Clinchant

Transformer-based models are nowadays state-of-the-art in ad-hoc Information Retrieval, but their behavior is far from being understood.

Ad-Hoc Information Retrieval Information Retrieval +1

Cannot find the paper you are looking for? You can Submit a new open access paper.