PinnedPrecision, Recall, and Desirability: A Deep DiveThis deep dive on precision, recall, and desirability discusses defining, motivating, measuring, identifying, and addressing these…Mar 272Mar 272
PinnedModeling 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.Dec 2, 20243Dec 2, 20243
PinnedHow 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 2, 20241Aug 2, 20241
PinnedAI-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 8, 20243Apr 8, 20243
PinnedSemantic 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
ChatGPT, Are You Just Telling Me What I Want to Hear?If I had completely different beliefs, would ChatGPT be as gleefully supportive of my perspective? Is it just saying what I want to hear?Mar 31Mar 31
Not All Recall is Created EqualWe should not improve recall for its own sake, nor assume all recall is equally valuable. Some relevant results matter more than others.Feb 241Feb 241
To Bot or Not to Bot: It Depends on the QuestionIf a machine can answer your question, ask the machine yourself. If your question requires a personal answer, explain why that is the case.Jan 31Jan 31
Ground Truth: A Useful FictionWhile we should not accept AI-generated outputs uncritically, we must acknowledge that our human-derived “ground truth” is a useful fiction.Jan 14Jan 14
Conjunction, Disjunction, What’s Your Function?Much of what search applications do is “hooking up words and phrases and clauses,” and conjunctions have played a key role in doing so.Jan 6Jan 6
