Elamur Research⌕
☰
home / authors / Thibault Formal

Thibault Formal

Thibault Formal has 2 papers in our library, in 2021, most of them on Information retrieval & search; often with Benjamin Piwowarski, Stéphane Clinchant.

2 papers in our library · 2021

OpenAlex · ORCID · Wikidata · h-index 11 · 39 works · 759 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 190 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #3487

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🏢NaverSeongnam-si · South Korea2020–2026 · 7 paperscurrent🎓Sorbonne UniversitéParis · France2020–2023 · 14 papers🔬Institut Systèmes Intelligents et de RobotiqueParis · France2022–2023 · 7 papers🔬LIP6Paris · France2020–2021 · 6 papers🔬Centre National de la Recherche ScientifiqueParis · France2023 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksComputer Vision and Pattern Recognition · 2 worksInformation Systems · 2 worksLanguage and Linguistics · 2 works

🧭 Topics 1Research subjects and languages the work is about.Information retrieval & search · 2 works

💡 Concepts 1Key ideas and methods explained on our concept pages.Inverted index · 1 work

 Works by year

2020s

20212 papers

 Papers

The most cited first (OpenAlex and our library).

  1. SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking (2021 · 512 citations)
    First-stage retrieval must pull candidate passages from a huge collection quickly. Classic bag-of-words rankers such as BM25 are fast because they use inverted indexes, but they miss relevant texts that phrase things differently from the query. Dense BERT retrievers handle that vocabulary mismatch, but they depend on…
  2. SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval (2021 · 83 citations)
    First-stage retrieval needs to be both accurate and fast. Dense retrievers do well but lack explicit term matching. Learned sparse models keep the benefits of bag-of-words search, such as inverted indexes, exact matching and interpretability. This paper improves SPLADE, a sparse model that turns BERT MLM logits into…

All works

3 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

  1. SPLADE: Sparse Lexical and Expansion Model for First Stage RankingInternational ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)Thibault Formal, Benjamin Piwowarski, Stéphane Clinchant2021 · 512 citations
  2. SPLADE v2: Sparse Lexical and Expansion Model for Information RetrievalarXiv:2109.10086Thibault Formal, Carlos Lassance, Benjamin Piwowarski, et al.2021 · 83 citations
  3. CoSPLADE : Adaptation d'un Modèle Neuronal Basé sur des Représentations Parcimonieuses pour la Recherche d'Information Conversationnelle ↗Actes de CORIA-TALN 2023. Actes de la 18e Conférence en Recherche d'Information et Applications (CORIA) · no summary yetNam Le Hai et al.2023

 Co-authors here

2 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 190 times (of the 149,439 papers whose bibliographies we read); 33 citing papers with a page here →.

Updated

This page in Markdown → https://md.research.elamur.ai/free/en/authors/thibault-formal/