📢 SEA December: A Year in IR in Amsterdam 🎇 With 8 speakers from the IR Amsterdam ecosystem: 3⃣ davidrau (U. Amsterdam) - The Role of Complex NLP in Transformers for Text Ranking 📄 4⃣ Bob van Luijt (@SeMI_Tech) - About Weaviate vector database. 1/2

Excited to share that our participation in TREC Interactive Knowledge Assistance Track 2023 ranked 1st! We submitted Retrieve-the-Generate and Generate-then-Retrieve runs,combining #LLMs & #search for conversational search. joint work with Zahra Abbasiantaeb davidrau Chuan Meng Hossein A. (Saeed) Rahmani Mohammad Aliannejadi

What’s a good baseline for RAG? 🤔 The literature shows consistent differences in experimental setups, retrievers, datasets, and metrics. So, we built the BERGEN library github.com/naver/bergen to enhance reproducibility and identify strong baselines : 🧵 NAVER LABS Europe

Context Embeddings for Efficient Answer Generation in RAG Speeds up generation time while improving answer quality by compressing multiple contexts into a small number of embeddings, offering flexible compression rates. 📝arxiv.org/abs/2407.09252

Context Embeddings for Efficient Answer Generation in RAG Proposes an effective context compression method to reduce long context and speed up generation time in RAG systems. The long contexts are compressed into to a small number of context embeddings which allow different

Happy to see our work on Context Embeddings for efficient answer generation in RAG being featured among other great works. Wang shuai (Dylan) Hervé Déjean Stéphane Clinchant

If you are at #EMNLP2024 and interested in RAG, come to discuss our BERGEN library! Vassilina Nikoulina will present the BERGEN poster tomorrow, Nov 13, 16:00-17:30, location: Jasmine Repo: github.com/naver/bergen Paper: aclanthology.org/2024.findings-… NAVER LABS Europe #NLProc #RAG

Incredibly proud to be building the best embedding models on the planet, alongside so many brilliant colleagues.