Semantic Search~BooleanBlkBelt and "ERE" and "6Sense" or "Resume Parsing"

Yes, Glen Cathey is a genius. That's not news. His take on Semantic Search is. Considering he is the black belt of Boolean search strings, hearing him discuss semantic search at the recent ERE Expo was eye opening. Recently, I attended a teleconference demo with the worldwide leadership of Last fall, they rolled out their semantic search for recruiters and companies. Now it's gaining popularity among job seekers.

Glen Cathey The Boolean Black Belt

I'm going to break the 500 word blogging rule and deep dive into content. Glen explained semantic search on his blog -here's the link

At the recent ERE Expo, The Boolean black belt said: "Stop wasting time creating difficult, complex Boolean search strings." That nearly knocked me off my chair. Glen had my attention.

He analyzed vendors that provide intelligent search, and suggests there's a place for them. It's not the only place of course, but hinted it makes sense, at times, to use applications that can do the work for you.

Semantic pattern recognition will change how we recruit in the future.

Give AI a string/cluster and semantic search uses artificial intelligence to do the work for you. Semantic Search on uses technology for Resume parsing. It takes a resume and chops it up by computer. It's intuitive. Parsing breaks down and extracts resume information, and it enables fielded contextual search.

Regardless of how sophisticated artificial intelligence becomes, we will ALWAYS need human beings to use the technology to make program, analyze, and interpret the data. Human sourcers can deduce potential experience, even with contradictory evidence, or the absence of information.

Semantic clustering, and unsupervised machine learning is a reality. We still have much to learn. I found it interesting that a person can program an algorithm to make decisions, using pattern recognition. AI aims to classify data patterns based on either prior knowledge, or on statistical information that's extracted from patterns.

Some applications use statistical methods in an attempt to understand key words with the same, or similar meanings within natural language parameters. Semantic sense tends to be close in units of google distance while words with dissimilar meanings tend to be farther apart.

One can use word and phrase variations, and fuzzy logic will pick up misspellings. Glen says “we ask too much of people to expect perfect resume." Some people might not know who to find the best key words to make their resumes stand out.

I've been communicating with about their 6Sense semantic search technology since February. I'm not going to assert I'm an expert on this topic, but I've been giving it careful consideration since the beginning of the year. The CIA doesn't use boolean search, in fact, if you suggested they do, they'd laugh in your face. They've been harnessing semantic search for quite some time. What does this have to do with recruiting?

Monster developed a unique product. They purchased the technology from Trovix (which is no longer in business).

Here's how monster describes their product:

"Developed through Monster's 2008 acquisition of search leader Trovix Inc., Monster's 6Sense patented semantic search technology utilizes intuitive, concept based searching, with a human-like understanding of the recruiting process and hiring needs. The 6Sense precision matching technology understands job titles, skills, experience level, industries, education and the hierarchy of concepts, evaluating a candidate's work experience like a recruiter would in a fraction of the time. While traditional keyword search engines are limited in their ability to distinguish concepts and meanings of words and cannot address things like recent vs. dated experience, the intelligence of the 6Sense technology contextually interprets the meaning behind words and concepts rather than relying on the narrow non intuitive search strings.

Monster's 6Sense technology boasts to reduce the time it takes to find the ideal candidate. One of their clients said it only took 3 days from the time he signed on to use 6Sense to source, interview, and make a placement. Cathey says, "It works well for position where titles effectively identify matches, and where there is a low volume and variety of key words. Glen is the consumer reports of search technology.

After all, he is the Boolean black belt. He reviewed artificial intelligence, and has written positive reports about monster's 6Sense technology.

There's been a lot of scuttlebutt of late that Job Boards are dead. They are not dead, in fact, they keep evolving and improving. Some recruiters say the big job boards like Monster are a last resort. However, in Cathey's report, he helped a fellow recruiter he was coaching find a candidate. And, guess where that candidate was?

As the technology for semantic search improves, the way we source and find candidates will follow suit. Boolean strings will always have a strong place in recruiting. My key point is simply this: we have to keep our minds open to all the new tools that come down the pike, apply critical thinking measures to determine which are best for our searches, and using critical thinking, make informed decisions.

Views: 393

Comment by Russell S. Moon III on April 24, 2010 at 3:39pm
Totally agree, what is "cutting edge" today can easily be obsolete in 6 months. Boolean is your base to build up from and I find that the understanding of Boolean Logic transposes to help you learn other search related concepts and their application more rapidly.
Comment by Margo Rose on April 24, 2010 at 5:55pm
The Semantic Technology via Pure Energy that scopes the entire open web is the future, and the present. We we have now can only get better. Thanks so much for reading my post.


You need to be a member of RecruitingBlogs to add comments!

Join RecruitingBlogs


All the recruiting news you see here, delivered straight to your inbox.

Just enter your e-mail address below


RecruitingBlogs on Twitter

© 2024   All Rights Reserved   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service