Communications of the ACM
Refine your search:
How the “Frontier” Became the Slogan of Uncontrolled AI
Artificial intelligence (AI) has been billed as the next frontier of humanity: the newly available expanse whose exploration …
From The Noisy Channel
Facets, But Which Ones?
This post dives into a particular challenge of faceted search, exploring the challenge of selecting which facets a search application should present to searchers...
From The Noisy Channel
Searching for Discovery
Search and DiscoveryIf search has one job, it is to help searchers find what they are looking for. However, many search application developers feel that searchHippocratic...
From The Noisy Channel
Where Do LTR Labels Come From?
The most common goal that my search clients express is a desire to improve their ranking. I always start by managing their expectations and helping them understand...
From The Noisy Channel
How to be a Search Consultant
If you have thought about hiring a search consultant or working as one, you may have asked yourself what exactly search consultants do. This post offers an opinionated...
From The Noisy Channel
Search and the Art of Conversation
What is the job of a search application? A common answer is that it needs to return the best results for a query, sorted in relevance order. While this answer sounds...
From The Noisy Channel
Is Search Trying Too Hard?
Last year, the emergence of ChatGPT and its ability to generate volumes from short prompts led me to speculate about the compressibility of thought. In a related...
From The Noisy Channel
Is Similarity Objective?
Some search problems have binary answers. We often frame these problems in terms of matching or equivalence. A simplistic formulation of relevance is that a canonicalized...
From The Noisy Channel
Bags of Documents and the Cluster Hypothesis
My writing on AI-powered search promotes the “bag-of-documents” model, which represents a search query as a distribution of vectors for relevant documents. When...
From The Noisy Channel
Bags of Queries as Sparse Document Representations
There is a duality between search queries and indexed documents: we can model a query as a bag of documents and a document as a bag of queries. This duality offers...
From The Noisy Channel
Is Targeted Advertising Ethical
Is Targeted Advertising Ethical?Targeted advertising is a huge industry with a massive branding problem. On one hand, nearly all of the “free” digital productspromoted...
From The Noisy Channel
Is Targeting Advertising Ethical?
Is Targeted Advertising Ethical?Targeted advertising is a huge industry with a massive branding problem. On one hand, nearly all of the “free” digital productspromoted...
From The Noisy Channel
Ranking vs. Relevance: 2 Pitfalls and How to Avoid Them
A crucial distinction for search applications is the difference between ranking and relevance. In this post, I explain what happens when search applications fail...
From The Noisy Channel
Sparse and Dense Representations
The heart of the AI-powered search revolution is the move from sparse bag-of-words representations to dense embedding-based representations. But reducing everything...
From The Noisy Channel
AI-Powered Search: Embedding-Based Retrieval and Retrieval-Augmented Generation (RAG)
When search application developers consider replacing a traditional search architecture with AI-powered search, they usually have two things in mind. The firstbag...
From The Noisy Channel
Analyzing the AI Search Opportunity
In the past several years, AI has disrupted every part of the technology industry. Search applications are no exception: it is not a question of whether to useinverted...
From The Noisy Channel
Learn to Rank = Learn to be Humble
As a search consultant, I work with lots of organizations that strive to improve their search applications. I tend to emphasize query understanding and contentlearning...
From The Noisy Channel
Hierarchy is Hard!
A fundamental concept in language understanding is that of semantic hierarchy. In linguistics, a hyponym is a more specific or subordinate word, while a hypernym...
From The Noisy Channel
An Update on Search Classes
In 2022, Grant Ingersoll and I launched our first four-week Search with Machine Learning class on Uplimit, then called Corise. I still have a special place in my...
From The Noisy Channel
Making Sense of Null and Low Results
With rare exception, searchers are unhappy when a search query returns zero results. Businesses — especially ecommerce businesses trying to sell products to searchers...
From The Noisy Channel