In January, during the fourth-quarter earning call Eric Schmidt hinted about 2009 being semantic year for Google. This is a key year; his company will start raiding semantic space. Lieutenants responded to CEO’s call and on 24th of March it become official that Google will provide better suggestions for related searches, based on semantic analysis of search strings. Since this development benefits everyone who uses Google, I did an analysis and comparison on this new feature.

Google users were already empowered with somewhat interesting feature on result pages, called “Searches related to”. Those who have never seen this feature can blame it on the positioning; it is at bottom of the page. This was a keyword modifier that varies the search keywords based on the suggestions, automatically generated by the Google. Query suggestion for single/compound words were already in place but this time company has taken a semantic approach on phrases.

Google’s Semantic Capabilities:

I performed a positive test with – Glaciers melting in Himalayas - as a non-quoted single phrase in the search box. The alternate query suggestions were certainly interesting. What especially caught my eye were two results: Global warming Himalayas and other one was climate change Himalayas (see Image).Skeptics might say you can achieve these results in other ways, but I believe Google when it says it’s gone semantic. Generating the options of “global warming” and “climate change” from “Glaciers melting” is certainly a semantic step forward. Many more semantic suggestions are possible, based on Polysemy and Synonimity but let us wait and watch till Google matures this technology.

Google’s current approach does well with single phrases, but does badly once you enter two or three phrases or something that can lead to multiple phrases. For example modify the above query string with “are” in-between. For example, when I modified the above query string with ‘are’ between Glaciers and melting—turning it into Glaciers are melting in Himalayas—the results fell flat and the query suggestions weren’t worth mentioning.  Since the company has said that they’re currently focusing only on single phrases, I’d say it’s a good beginning.

Alternatives:

Generating related search strings  exist in all search engines for more then a decade. Each engine shows the “Related Searches” feature somewhere in their result page, Top or bottom its all about positioning. The questions are, what does Google do that other search engines don’t?  What can’t Google do that others can?

When it comes to related keywords suggestion one search engine, which stands out, is ASK.

ASK

Depending upon the understanding of your phrase, keywords and inter-relation of your words, ASK comes up with suggestions which can expand, narrow and sometime give you different line of thought (on keywords selection). Searches, which are done from a browser toolbar of the ASK, have the suggestions segregated in two categories expand and narrow your keywords (this only happens for me from browser toolbar search, do not know why).

You can see ‘Related Searches’ prominent on the right-hand-side of your result page.  The positioning of the suggestions and their segregation into swelling and shrinking categories are nice features.  Google’s suggestions look more semantic than ASK’s, but ASK currently gives more suggestions and is much more user-friendly.

Cluuz

Cluuz engine cannot escape the comparison, as its approach to related keyword suggestion is completely different from others. To begin with – try out any keyword in this engine, and you will not be disappointed, but there will neither be a surprise. Strength of query suggestion of this engine does not come from clustering or semantics but from its workflow.

Cluuz is a named entity extraction engine, it can extract people, websites, addresses, email address and phone numbers from the results and display them separately. Once you select any extracted entity it modifies query string with it, and shows new set of results. So  you can modify your search results by driving through extracted named entities, it is a slam-dunk. I tried out “carbon credits” in this engine and image has a impression of it.

The others

The majority of other search engines have perfected the art of understanding important keywords.  Generally, these are nouns, proper nouns, or noun phrases, and engines hold the taxonomical references of the important words in predefined categories. Such engines do not use any high-end semantic or  clustering mechanisms. They calculate the probability or “weight of your keywords” in “a category” and then display the category entries. Cuil and Kosmix are the examples of such engines, Cuil provides more categories and has more depth then Kosmix. However, broad classification of related keywords isn’t very useful to a web searcher, as it would be quicker to search one’s own memory for related words.

Yahoo and MSN both do the “query suggestion” but their output is not interesting, at current moment.

Google’s approach to semantics:

In one of my earlier blogs**, I did the analysis and comparison of semantic engines like Hakia. But Google’s latest approach on the semantic searching is worlds apart, and behind by one generation. While Hakia tries to understand your phrases and tries to match your expectations on the source documents semantically, Google is giving you option of changing your keywords semantically as it cannot search semantically.

Hakia’s approach is certainly much better, as it makes an effort to understand what you write, but its indexes, popularity, and engineering efforts currently don’t match those of Google.  Therefore, Google’s new feature is a consolation for Google searchers—it’s better to have something semantic than nothing.

---

Note:
Search engines reviewed here are the ones capable of finding information on the whole of World Wide Web. Engines like Powerset are left out because of same reason.

Clustering engines have not been considered for this review because their modulus operandi is hierarchical by nature, hence supporting “query suggestion” by default. But providing the semantic replacement for each cluster is not possible, as clusters are generally broken down to the word levels.

---

Reference: Quest for perfect Search Engine –Part1

• «Previous Post
• Next Post »

---