activity
20172022
most citedFrom Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective

15 citations · 35 across the 8 of their papers we have counts for

collaborators

8 papers

cs.IR202111 cited

SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval

Thibault Formal, Carlos Lassance, Benjamin Piwowarski +1

In neural Information Retrieval (IR), ongoing research is directed towards improving the first retriever in ranking pipelines. Learning dense embeddings to conduct retrieval using…

cs.CL2021

Efficient Inference for Multilingual Neural Machine Translation

Alexandre Berard, Dain Lee, Stéphane Clinchant +2

Multilingual NMT has become an attractive solution for MT deployment in production. But to match bilingual quality, it comes at the cost of larger and slower models. In this work,…

cs.CL20211 cited

Masked Adversarial Generation for Neural Machine Translation

Badr Youbi Idrissi, Stéphane Clinchant

Attacking Neural Machine Translation models is an inherently combinatorial task on discrete sequences, solved with approximate heuristics. Most methods use the gradient to attack t…

cs.IR20212 cited

SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking

Thibault Formal, Benjamin Piwowarski, Stéphane Clinchant

In neural Information Retrieval, ongoing research is directed towards improving the first retriever in ranking pipelines. Learning dense embeddings to conduct retrieval using effic…

cs.IR20201 cited

A White Box Analysis of ColBERT

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. Recent work has claimed that BERT does not…

cs.CL2019

On the use of BERT for Neural Machine Translation

Stéphane Clinchant, Kweon Woo Jung, Vassilina Nikoulina

Exploiting large pretrained models for various NMT tasks have gained a lot of visibility recently. In this work we study how BERT pretrained models could be exploited for supervise…