PinnedDaniel TunkelangWhere Do LTR Labels Come From?My clients often express a desire to improve their ranking. This post sketches out challenges of obtaining labeled training data for LTR.Aug 6Aug 6
PinnedDaniel TunkelangHow to be a Search ConsultantIf you have thought about hiring a search consultant or working as one, you may have asked yourself what exactly search consultants do.Aug 21Aug 21
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).Apr 83Apr 83
PinnedDaniel TunkelangPrecision, Recall, and DesirabilitySearch focuses on precision, recall, and desirability. AI mostly helps with the first two, which makes it possible to focus on the third.Feb 152Feb 152
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).Aug 7, 20231Aug 7, 20231
Daniel TunkelangQuo Vadis Nunc, Quora?Although I stopped contributing to Quora, I care deeply about technology-enabled knowledge sharing. So I am curious to see where it goes.Sep 25Sep 25
Daniel TunkelangSeriously or Literally?Search applications to take searchers seriously, not literally. This need holds even when searchers practically ask to be taken literally.Sep 18Sep 18
Daniel TunkelangCold Start, Practical EditionIn practice, the cold start problem usually requires more than just collecting behavioral data to train a machine-learning model.Sep 16Sep 16
Daniel TunkelangAll Else EqualAn A/B test only holds if we hold all else equal. However, the test also assumes the current state of the world. What if the world changes?Sep 10Sep 10
Daniel TunkelangTake Searchers Seriously, Not LiterallyMany search developers take a literal approach to query understanding. Their misguided attempt to respect searcher intent can causes harm.Sep 4Sep 4