acm-header
Sign In

Communications of the ACM

Blogroll


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

Opportunity Analysis for Search
From The Noisy Channel

Opportunity Analysis for Search

I’m a big fan of opportunity analysis. I’ve seen far too many organizations underinvest in opportunity analysis and thus waste enormous — and avoidable — effort...

Thank you for the kind words!
From The Noisy Channel

Thank you for the kind words!

Thank you for the kind words!If I follow you, then you are pointing out that, by generating revenue through promoted search, a business can funnel that revenue...

Promoted Search: A Follow-Up
From The Noisy Channel

Promoted Search: A Follow-Up

My post on promoted search results drew some pointed feedback. People asked me what kind of promoted search behavior I deem acceptable, as well as whether I saw...

Thoughts on Promoted Search Results
From The Noisy Channel

Thoughts on Promoted Search Results

I’m not a fan of ads. So you might expect me to be violently opposed to promoted search results — search engine results that are optimized for something other than...

When There’s No Conversion Rate
From The Noisy Channel

When There’s No Conversion Rate

If your business depends on search, it’s critical to track search effectiveness using an evaluation methodology. In my experience, most organizations rely on implicit...

Measuring Search Effectiveness
From The Noisy Channel

Measuring Search Effectiveness

Delivering effective search starts with defining how to measure effectiveness.The information retrieval community has been evaluating search for decades. Established...

Defining relevance is a topic in its own right.
From The Noisy Channel

Defining relevance is a topic in its own right.

Defining relevance is a topic in its own right. You typically collect either explicit human judgments or implicit judgements from behavior, and then you use those...

Supporting the Searcher’s Journey: When and How
From The Noisy Channel

Supporting the Searcher’s Journey: When and How

Sometimes, search is simple. The searcher types a few words into the search box, retrieves a ranked list of results, and selects the right one. Easy peasy.Other...

I think the even more interesting case for using supply or demand is where supply vastly outstrips…
From The Noisy Channel

I think the even more interesting case for using supply or demand is where supply vastly outstrips…

I think the even more interesting case for using supply or demand is where supply vastly outstrips demand and most intents are in the tail, e.g., searching through...

You already see it on Amazon.
From The Noisy Channel

You already see it on Amazon.

You already see it on Amazon. Do a search for “matrix”: not only do you only see Keanu Reeves movie results on the first page, but the left rail focuses on movies...

Search: Intent, Not Inventory
From The Noisy Channel

Search: Intent, Not Inventory

When I enter a physical store, my intent is “I want to buy X” or “I’m looking for something in order to do X.” It’s not “Show me the products that satisfy characteristics...

Dances with HiPPOs
From The Noisy Channel

Dances with HiPPOs

Decision making, especially at technology companies, is supposed to be data-driven. Unfortunately, even in this wondrous age of science, decisions often depends...

Martin, thanks for the kind words.
From The Noisy Channel

Martin, thanks for the kind words.

Martin, thanks for the kind words. The TunkRank that Jason Adams implemented has been down for a while. I’m not aware of any other implementation that is available...

I’m hardly an expert on legal IR. But here are a few pointers:
From The Noisy Channel

I’m hardly an expert on legal IR. But here are a few pointers:

I’m hardly an expert on legal IR. But here are a few pointers: Passage retrieval in legal texts [PDF] Passage Retrieval Starting from Patent Claims A Clef-Ip 2013...

I can only offer high-level guidance in a comment thread.
From The Noisy Channel

I can only offer high-level guidance in a comment thread.

I can only offer high-level guidance in a comment thread. But it sounds like you might benefit from collecting trigrams as well as bigrams. If mug tree stands are...

I discuss it a bit in this post: https://queryunderstanding.com/query-expansion-2d68d47cf9c8
From The Noisy Channel

I discuss it a bit in this post: https://queryunderstanding.com/query-expansion-2d68d47cf9c8

I discuss it a bit in this post: https://queryunderstanding.com/query-expansion-2d68d47cf9c8

Broad and Ambiguous Search Queries
From The Noisy Channel

Broad and Ambiguous Search Queries

A typical approach for processing search queries is to retrieve a set of matching documents and then rank them with a relevance scoring function. This simple approach...

Premature Optimization is (Still) the Root of All Evil
From The Noisy Channel

Premature Optimization is (Still) the Root of All Evil

A lesson that we software engineers learn early in our careers is that “premature optimization is the root of all evil.” This gem of advice from the inimitableDonald...

Is Relevance Part of the Problem?
From The Noisy Channel

Is Relevance Part of the Problem?

Much of the innovation in information retrieval and recommender systems focuses on better targeting in order to improve relevance. Those of us who develop suchin...

Thanks Tony!
From The Noisy Channel

Thanks Tony!

Thanks Tony! And you’re right thatI’m oversimplifying. My excuse is that it was already a 2,000-word post. :-)
Sign In for Full Access
» Forgot Password? » Create an ACM Web Account