Fetching the paper…

Reading the bibliography…

2023

Naver Labs Europe (SPLADE) @ TREC Deep Learning 2022

Lassance, Carlos, Clinchant, Stéphane

Original
PDF
Post on X

Understand

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

We submitted runs to all four tasks, with a focus on the full retrieval passage task.
The strategy is almost the same as 2021, with first stage retrieval being based around SPLADE, with some added ensembling with ColBERTv2 and DocT5.
We also use the same strategy of last year for the second stage, with an ensemble of re-rankers trained using hard negatives selected by SPLADE.

Naver Labs Europe (SPLADE) @ TREC Deep Learning 2022 · Around

Built on

A probabilistic analysis of the rocchio algorithm with tfidf for text categorization
Joachims, T. (1996) · 1996
Earlier work this paper cites.
Document ranking with a pretrained sequence-to-sequence model
Original
Nogueira, R., Jiang, Z., and Lin, J. (2020) · 2003
Earlier work this paper cites.
From doc2query to doctttttquery
Nogueira, R. and Lin, J. (2019) · 2019
Earlier work this paper cites.

Similar

Rethink training of bert rerankers in multi-stage retrieval pipeline
Gao, L., Dai, Z., and Callan, J. (2021) · 2021
Cited alongside, same era.
Colbertv2: Effective and efficient retrieval via lightweight late interaction
Original
Santhanam, K., Khattab, O., Saad-Falcon, J., Potts, C., and Zaharia, M. (2021) · 2021
Cited alongside, same era.
ranx. fuse: A python library for metasearch
Bassani, E. and Romelli, L. (2022) · 2022
Cited alongside, same era.

Then

From distillation to hard negative sampling: Making sparse neural ir models more effective
Original
Formal, T., Lassance, C., Piwowarski, B., and Clinchant, S. (2022) · 2022
Later among the works it cites.
An efficiency study for splade models
Lassance, C. and Clinchant, S. (2022) · 2022
Later among the works it cites.
Rankt5: Fine-tuning t5 for text ranking with ranking losses
Zhuang, H., Qin, Z., Jagerman, R., Hui, K., Ma, J., Lu, J., Ni, J., Wang, X., and Bendersky, M. (2022) · 2022
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…