Billions over billions of Dollars have probably invested in optimizing search engine algorithms. Just think of Microsoft’s recent release of Bing, designed to challenge the mighty search engine power of Google, not mentioning all those smaller, less attractive, and less effective search websites, living a miserable life in the shadow of the big two (I exclude Yahoo as a search engine these days.) Add to this the numerous, yet unsuccessful attempts by start-ups all over the world to provide better search results.
Having a masters degree in Electrical Engineering myself, I don’t doubt the necessity of complex algorithms that allow to produce search results from millions of websites within seconds. I don’t doubt the massive investment of money and manpower to provide us, the Internet users, with the information we are looking for.
However, I am nothing short of stupefied by the dumb-as-dumb-can-be search results I receive frequently. We are living in the 21st century. Computers listen to our voice, and they answer. Computers recognize traffic patterns and control traffic accordingly. Yet, computers cannot distinguish between the city of Boston and the rock band Boston. They tell you to enter your question like a regular sentence as if you were talking to a human. But this is where the intelligence stops. The search results – millions of them – are discouraging.
The ineffectiveness of presenting search results has been confirmed by an article I read recently in the online version of the New York Times (See: http://bits.blogs.nytimes.com/2010/07/16/google-buys-metaweb-to-improve-search-results/?hpw). Here is an excerpt:
There are some Web searches that Google doesn’t handle so well — like finding a famous person’s birthday, or searching for a word that means many different things. Search for “Boston,” for example, and all the top links are about the city in Massachusetts. But Boston is also the name of a band and 26 other cities.
Google said Friday that in an effort to improve these tricky types of search queries, it was buying Metaweb, a San Francisco start-up that says it makes Web sites smarter.
Hey, Google and Bing! Meet 44 Year Old ELIZA!
You may call me old-fashioned, but many, many years ago in a different lifetime of mine I played with a programming language called BASIC. I don’t even know if versions of BASIC still exist. The latest version, I believe, comes in form of Microsoft’s VisualStudio that includes an advanced version of VisualBasic. The most interesting, because interactive, program I found was ELIZA. The program listing (i.e. the source ode) for ELIZA fits on three pages of a standard 8.5″ x 11″ paper sheet. The results are, nevertheless, amazing.
ELIZA asks questions and responds intelligently to the user’s input. In scientific terms, “ELIZA is concerned with: (1) the identification of key words, (2) the discovery of minimal context, (3) the choice of appropriate transformations, (4) generation of responses in the absence of key words. ELIZA is a program which makes natural language conversation with a Computer possible.” (Source: ELIZA – A Computer Program For the Study of Natural Language Communication Between Man And Machine by Joseph Weizenbach, Massachusetts Institute of Technology, Cambridge, Mass., January 1966)
Looking at attributes like identification of keywords, discovery of minimal context, choice of appropriate transformations, generations of responses in the absence of keywords… Isn’t that exactly what we are looking for in a search engine? I wouldn’t mind some additional responses like “Do you mean the city or the rock band?”
Isn’t it amazing that Google spends millions in an effort to keep up with Bing? Bing, after all, provides better search results, but it still is no ELIZA. You can buy the document ELIZA – A Computer Program For the Study of Natural Language Communication Between Man And Machine for a mere $15! Just log on to http://portal.acm.org/citation.cfm?id=365168&dl=GUIDE&coll=GUIDE&CFID=95147346&CFTOKEN=39216600.
Demo Session With ELIZA
Well, the most popular application for ELIZA was resembling a psychologist, and that is clearly demonstrated in the session demo below. The responses are, nevertheless, amazing. The session also demonstrates convincingly the effective analysis of keywords and the generation of intelligent responses. As I mentioned before, the program listing is amazingly short. See http://home.cmit.net/rwolbeck/programmingtutorial/code/eliza.htm as an example.
Men are all alike
IN WHAT WAY
They’re always bugging us about something or other.
CAN YOU THINK OF A SPECIFIC EXAMPLE
Well, my boyfriend made me come here.
YOUR BOYFRIEND MADE YOU COME HERE
He says I’m depressed much of the time.
I AM SORRY TO HEAR YOU ARE DEPRESSED
It’s true. I am unhappy.
DO YOU THINK COMING HERE WILL HELP YOU NOT TO BE UNHAPPY
I need some help, that much seems certain.
WHAT WOULD IT MEAN TO YOU IF YOU GOT SOME HELP
Perhaps I could learn to get along with my mother.
TELL ME MORE ABOUT YOUR FAMILY
My mother takes care of me.
WHO ELSE IN YOUR FAMILY TAKES CARE OF YOU
My father.
YOUR FATHER
You are like my father in some way.
WHAT RESEMBLANCE DO YOU SEE
You are not very aggressive but I think you don’t want me to notice that.
WHAT MAKES YOU THINK I AM NOT VERY AGGRESSIVE
You don’t argue with me.
WHY DO YOU THINK I DON’T ARGUE WITH YOU
You are afraid of me.
DOES IT PLEASE YOU TO BELIEVE I AM AFRAID OF YOU
My father is afraid of everybody.
WHAT ELSE COMES TO MIND WHEN YOU THINK OF YOUR FATHER
Bullies.
DOES THAT HAVE ANYTHING TO DO WITH THE FACT THAT YOUR BOYFRIEND MADE YOU COME HERE
[
[
