acm-header
Sign In

Communications of the ACM

Blogroll


Refine your search:
dateMore Than a Year Ago
authorDaniel Tunkelang
bg-corner

AI for Query Understanding
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...

Query Understanding
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...

Recall: Size Isn’t Everything
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...

The 3 Rs of Search: Relevance, Recall, and Ranking
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...

In Search of Recall
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...

Putting Users Back In Control
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...

Facets of Faceted Search
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...

Expanding on Explore-Exploit
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...

Wolf, thank you for these additional points.
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...

Coffee, Coffee, Coffee!
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...

Learning from Friction to Improve the Search Experience
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...

Thanks. And sorry that slide was cryptically brief.
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...

In this case, I’m imagining that the only match of the string “black” against one of the attributes…
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...

The typical integration approach I’ve seen is to use a separate query rewriting service that then…
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...

If the results for two queries expressing the same intent are similar, then they should map to…
From The Noisy Channel

If the results for two queries expressing the same intent are similar, then they should map to…

If the results for two queries expressing the same intent are similar, then they should map to similar vectors. If not, then it’s more complicated. You might still...

Indeed, the devil is in the details, But I can tell you that I’ve successfully used this idea to…
From The Noisy Channel

Indeed, the devil is in the details, But I can tell you that I’ve successfully used this idea to…

Indeed, the devil is in the details, But I can tell you that I’ve successfully used this idea to drive lift for my clients, and I recommend exploring it.

As I suggested in the post, you can use the embeddings of result titles for the results searchers…
From The Noisy Channel

As I suggested in the post, you can use the embeddings of result titles for the results searchers…

As I suggested in the post, you can use the embeddings of result titles for the results searchers engage with when they perform the query. I realize that the devil...

I’ve written a few posts that at least touch on voice interfaces:
From The Noisy Channel

I’ve written a few posts that at least touch on voice interfaces:

I’ve written a few posts that at least touch on voice interfaces: Query Understanding and Voice Interfaces Why Voice isn’t Selling…Yet Query Understanding and Chatbots...

Search Queries and Search Intent
From The Noisy Channel

Search Queries and Search Intent

Mapping Search Queries To Search IntentsEvaluating and improving search experience starts with analyzing the queries searchers are making. But search queries are...

MMM, Search!
From The Noisy Channel

MMM, Search!

This morning, I had the pleasure of being hosted by Grant Ingersoll to talk about search with his team at the Wikimedia Foundation.Wikipedia is an indispensable...
Sign In for Full Access
» Forgot Password? » Create an ACM Web Account