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
Using AI to Understand Search Intent
Several weeks ago, I wrote a post advocating the use of AI for query understanding. I argued that holistic query understanding with embeddings and deep learning...
From The Noisy Channel
The Eternal Quest for Meaning
In 1668, John Wilkins published An Essay Towards a Real Character, and a Philosophical Language. In it, he proposed a universal language that would represent every...
From The Noisy Channel
Ranking vs. Relevance
Most folks who work on search worry about relevance. But it’s surprisingly difficult to find a useful definition of relevance.Defining RelevanceMerriam-Webster ...
From The Noisy Channel
Putting Search Ranking in Perspective
For feeds and recommendations, ranking is critical. All the inputs are implicit, so machine-learned ranking is the only practical way to optimize engagement.Search...
From The Noisy Channel
New Choice
In improv, there’s a fun game called “new choice”. At any point during the improvised scene, the host can call for a “new choice”. The player who last spoke has...
From The Noisy Channel
AI for Query Understanding
In the past decade, the incredible progress in word embeddings and deep learning has fueled an interest in neural information retrieval. An increasing number of...
From The Noisy Channel
Query Understanding
This publication is a series of posts devoted to query understanding. Each post is self-contained, but there is a natural progression. If you’d like to read them...
From The Noisy Channel
Recall: Size Isn’t Everything
Recall is a key measure of search quality that doesn’t always get the attention it deserves. But how does a search engine recognize when recall is a problem?Size...
From The Noisy Channel
The 3 Rs of Search: Relevance, Recall, and Ranking
In grade school, we were taught the three Rs: reading, writing, and ‘rithmetic. In search, we can be thankful that the three Rs actually start with the letter R...
From The Noisy Channel
In Search of Recall
Search developers tend to focus most of their efforts on the first page of results. As a result, they prioritize investment in ranking models, with the goal ofprecision...
From The Noisy Channel
Putting Users Back In Control
Francis Fukuyama, Barak Richman, and Ashish Goel recently published a piece in Foreign Affairs, which they ambitiously titled “How to Save Democracy From Technology...
From The Noisy Channel
Facets of Faceted Search
Faceted search is a fascinating topic. It’s a standard feature of site search, and one could write an entire book on the subject. In this post, I’ll focus on some...
From The Noisy Channel
Expanding on Explore-Exploit
A few years ago, I proposed a non-adversarial ad-supported model: an explore-exploit model, applicable to search engines and feeds, that aligns the interests of...
From The Noisy Channel
Wolf, thank you for these additional points.
Wolf, thank you for these additional points. I agree that Peter Norvig’s post, while very educational, is a starting point to learn about spelling correction but...
From The Noisy Channel
Coffee, Coffee, Coffee!
In 1984, Robin Williams starred in Moscow on the Hudson as a Russian saxophonist who decides to defect from the USSR during a shopping trip to a New York department...
From The Noisy Channel
Learning from Friction to Improve the Search Experience
When we design search applications, we aspire to make the user experience frictionless. A search engine should “just work”, enabling searchers to easily express...
From The Noisy Channel
Thanks. And sorry that slide was cryptically brief.
Thanks. And sorry that slide was cryptically brief. What I mean is that spelling correction should not restrict itself to correcting each token separately. Many...
From The Noisy Channel
In this case, I’m imagining that the only match of the string “black” against one of the attributes…
In this case, I’m imagining that the only match of the string “black” against one of the attributes is for the “color” attribute. If the string matches multiple...
From The Noisy Channel
The typical integration approach I’ve seen is to use a separate query rewriting service that then…
The typical integration approach I’ve seen is to use a separate query rewriting service that then either filter the Solr query to the preferred categories / attributes...
From The Noisy Channel