PinnedDaniel TunkelangRanking vs. Relevance: 2 Pitfalls and How to Avoid ThemRelevance takes priority over desirability, but desirability dominates small differences in probability of relevance.3 min read·Apr 29, 2024----
PinnedDaniel TunkelangLLMs and RAG are Great, But Don’t Throw Away Your Inverted IndexIt is tempting to believe that we can dispense with the inverted index in favor of embedding-based retrieval. But there are a few…3 min read·Mar 29, 2024----
PinnedDaniel TunkelangSparse and Dense RepresentationsAI-powered search moves from sparse bags of words to dense embedding-based representations. But sparse vs. dense is a false dichotomy.6 min read·Apr 15, 2024----
PinnedDaniel TunkelangAI-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).9 min read·Apr 8, 2024--3--3
PinnedDaniel TunkelangSemantic 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).1 min read·Aug 7, 2023--1--1
Daniel TunkelangIs Targeted Advertising EthicalUsers have — or should have — two choices: pay cash or accept targeted advertising. There is no free lunch.4 min read·May 7, 2024--1--1
Daniel TunkelangLLMs and RAG are great. What’s Next?In the next few years, I believe that we will see LLMs focus less on size and more on function calling and tool use.7 min read·Apr 18, 2024----
Daniel TunkelangAnalyzing the AI Search OpportunityIt’s not a question of whether to use AI for search, but where to incorporate it into the stack. And it’s important not to break what…5 min read·Apr 2, 2024----
Daniel TunkelangLearn to Rank = Learn to be HumbleThe bottleneck for improving ranking is available training data — not just quantity, but its alignment with opportunities for improvement.3 min read·Mar 24, 2024----
Daniel TunkelangHierarchy is Hard!Organizing product types or topics into a taxonomy is challenging, but queries present an even more daunting challenge.4 min read·Mar 14, 2024----