Can machines really understand text?

No, but Sherlock can instantly generate Concept Maps from texts, in any language!

WhAT's it for?Testimonials

Faster and better with Sherlock

Quote

 "Sherlock's correlation engine seems to me like it could become as common as search button functionality is today: an automated way to make sense of complex document collections" 

Vinay Gupta ~ Crypto Wizard and CEO Mattereum

Example: Remixing Wikipedia 


Check out the video to see how Sherlock helps you quickly find key evidence in the World's biggest encyclopedia. From Trump to Trump Tower in Moscow in a minute.

Smarter research is on its way, are you ready? Click to find out!

Sign out

No lingo? No problemo!

Listen in to what you can't understand! Extending news gathering reach past the language constraints of analysts and reporters. 

Check out these archive examples in Chrome, Arabic and Russian

Does it work?

Quote

 "We found Sherlock combined rigour with elegance to power the deep textual insights we needed in finance and technology"

Michael Mainelli

Emeritus Gresham Professor of Commerce at Gresham College in London,  founder of the Long Finance initiative, he was elected Sheriff of the City of London on 24 June 2019.

Why it works

Quote

"If the facts don't hang together on a latticework of theory, you don't have them in a usable form."

- Charlie Munger

Check out Charlie!
Charlie Munger

How it works

Sherlock's Lattice, Concept Maps

Produced by Morgan State University, this diagram describes the benefits of the approach. Their website has a very readable tutorial available, in which they spell out guidelines for the manual production of maps. Sherlock follows them, and is, as far as we know, the first autonomous process on the planet to do so.

Card image cap

The big picture

It may sound odd to think of an idea as something that can be found in text, but that is how we store and transfer ideas. We package them in sequential nested chunks that make them easier to digest. Once the packaging is removed the patterns emerge, as words that are frequently seen together to denote the underlying idea.

The word "idea" is derived from old Greek that means "to have seen". If you want to hear how noticing coincidences formed the original notion of 'idea', and how it remains central to Cognitive Science, check out this podcast from Oxford's Bettany Hughes

Better intention and design

Ethical by design

Sherlock finds the common ideas that bind groups together, and needs no further information than the words written. 

The process is easily explained, and fully traceable, because the answers are in the sources, verbatim.

It doesn't need, use,  or store private data. Privacy is baked into the design.

Always up to date

No more retraining, no more parameter tweaking. If an earthquake occurs, or a new political sensation invades the press, new names will baffle supervised text-mining techniques. 

Sherlock works from a list of what to ignore, so new stuff gets handled automatically, just so long as it is frequent.

Multilingual

Sherlock has been tried on more than thirty languages, including Arabic and Russian. It is completely grammar agnostic, and will work on any language, human or computer, for which a stop word list can be provided.

Balanced

Sherlock tries to be as autonomous as possible, requiring just two parameters, how robust the patterns need to be, and how many words will be enough.  

For example, the UK Brexit survey takes 75% pattern confidence, and 20 words

© Copyright 2014-2019 Christopher Painter- All rights reserved.