acm-header
Sign In

Communications of the ACM

Blogroll


bg-corner

AI-Powered Search: Embedding-Based Retrieval and Retrieval-Augmented Generation (RAG)
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...

Analyzing the AI Search Opportunity
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...

Learn to Rank = Learn to be Humble
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...

Hierarchy is Hard!
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...

An Update on Search Classes
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...

Making Sense of Null and Low Results
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...

Precision, Recall, and Desirability
From The Noisy Channel

Precision, Recall, and Desirability

Recent developments in AI have created opportunities across the search stack. But before building solutions, it is important to clearly identify the problems they...

Retroactive Loss of Privacy
From The Noisy Channel

Retroactive Loss of Privacy

We live in an age where we increasingly feel a loss of privacy. Much of our communication, media consumption, and shopping is mediated through platforms that track...

Random Thoughts on Interestingness
From The Noisy Channel

Random Thoughts on Interestingness

As a computer scientist and an information scientist, I have always been fascinated by fundamental questions of computational complexity and compressibility. These...

Query Specificity
From The Noisy Channel

Query Specificity

The central challenge of query understanding is mapping a query to a representation of the searcher’s intent. Recognizing when two or more different search queries...

Query Understanding and Ecommerce
From The Noisy Channel

Query Understanding and Ecommerce

Yesterday, I had the privilege to deliver a “last lecture” at eBay, where I have been working with the query science team for nearly 6 years. I took the opportunity...

Indexing by Intent
From The Noisy Channel

Indexing by Intent

Search developers mostly focus on mapping queries to results. This perspective is natural, insofar as search starts with the user formulating a query and (hopefully)...

Using Retrievability to Measure Recall
From The Noisy Channel

Using Retrievability to Measure Recall

In court, witnesses swear to tell “the whole truth and nothing but the truth.” Search engines are not under oath, but they should be truthful.Two metrics for search...

Search vs. Browse
From The Noisy Channel

Search vs. Browse

One of the oldest distinctions in information access is between searching and browsing. Does a user initiate an information-seeking journey by typing keywords into...

When Machine Learning Hits A Wall
From The Noisy Channel

When Machine Learning Hits A Wall

Machine learning (or AI if you prefer) is amazing. I cannot think of another area of computer science — or of technology in general — that has been more influential...

Critical Thinking and Generative AI
From The Noisy Channel

Critical Thinking and Generative AI

Critical Reasoning and Generative AIOne of the formative experiences in my mathematics education was a time I struggled to compute an integral in a calculus class...

Semantic Equivalence of e-Commerce Queries
From The Noisy Channel

Semantic Equivalence of e-Commerce Queries

I am proud to share the slides for “Semantic Equivalence of e-Commerce Queries”, which my eBay colleague Aritra Mandal presented this morning at the KDD 2023 Workshop...

Upcoming Search Classes this Fall
From The Noisy Channel

Upcoming Search Classes this Fall

I hope that everyone has been enjoying the summer. I took a sabbatical from teaching, but I’m looking forward to new students this fall.Are you excited to learn...

What is Searcher Happiness?
From The Noisy Channel

What is Searcher Happiness?

As a search specialist, my main goal is to improve searcher happiness. Sure, companies pay me to improve business metrics like conversion rate and revenue, butprobability...

Surprise! Surprise?
From The Noisy Channel

Surprise! Surprise?

We have reached the stage of generative AI where artists, authors, and performers are convinced that AI is stealing their lives — and, perhaps more importantly,...
Sign In for Full Access
» Forgot Password? » Create an ACM Web Account