PinnedDaniel Tunkelang·May 19The Bag-of-Documents Model for Query Understanding and RetrievalToday I presented my recent work on the bag-of-documents model as part of a series of talks hosted by Trey Grainger and Doug Turnbull.
PinnedDaniel Tunkelang·Apr 20Distilling Retrieval Pipelines to a Single Embedding ModelA Pretrained Bag-of-Documents Model for Product SearchA response icon1A response icon1
PinnedDaniel Tunkelang·Dec 2, 2024Modeling Queries as Bags of DocumentsLast week, I had the honor of presenting “Modeling Queries as Bags of Documents” at Search Solutions 2024 with Aritra Mandal.A response icon3A response icon3
PinnedDaniel Tunkelang·Apr 8, 2024AI-Powered Search: Embedding-Based Retrieval and Retrieval-Augmented Generation (RAG)Replacing traditional search with AI-powered search means embedding-based retrieval and possibly retrieval-augmented generation (RAG).A response icon4A response icon4
PinnedDaniel Tunkelang·Aug 7, 2023Semantic Equivalence of e-Commerce QueriesSemantic Equivalence of e-Commerce Queries by Aritra Mandal, Daniel Tunkelang, and Zhe Wu. KDD 2023 Workshop on E-Commerce and NLP (ECNLP).A response icon1A response icon1
Daniel Tunkelang·Mar 26Agentic Search as an Agile Engineering ProcessAgentic search does more than retrieve. It behaves less like a function call and more like an engineering workflow that benefits from agile.
Daniel Tunkelang·Mar 9What Are Today’s AI Fundamentals?Are the classical AI foundations still the right ones? Or has the center of gravity shifted from algorithms to systems?A response icon1A response icon1
Daniel Tunkelang·Jan 5The History of SimilaritySimilarity has a long, consequential intellectual history. Only recently do we understood it as dependent on context, purpose, and use.A response icon1A response icon1
Daniel Tunkelang·Dec 15, 2025Does Retrieval Still Matter?The future is not answers versus retrieval. It is answers by default and retrieval for tasks that require transparency, control, and nuance.A response icon1A response icon1
Daniel Tunkelang·Dec 9, 2025Relevance: The Outer LimitsThe bag-of-documents model computes the center of relevant content, but not how far from that center retrieval should explore.
