[Sigia-l] Natural Language Searching vs Keyword Searching

[Gary Carlson]

Natural Language Search would need to use Natural Language Processing
(NLP).  An excellent description of NLP can be found at
http://research.microsoft.com/nlp/.  

Natural Language Search would imply that a user can "ask a question".
Then, whatever technology is living under the sheets would take a stab
at parsing, the question resolving ambiguities (was that a "tank" as in
Boom boom or a "tank" is in Nemo's abode) and then looking for
information in whatever corpus it is searching.  There are a number of
ways that these technologies can identify the concepts that were "asked"
and then find similar ones in the corpus.


-----Original Message-----
From: sigia-l-admin at asis.org [mailto:sigia-l-admin at asis.org] On Behalf
Of Tanya Rabourn
Sent: Friday, February 20, 2004 2:41 PM
To: sigia-l at asis.org
Subject: RE: [Sigia-l] Natural Language Searching vs Keyword Searching


On Fri, 20 Feb 2004, Gary Carlson wrote:
> In my limited experience I came to the following, subjective,
> conclusions.  Natural Language processing (along with Baysian, vector
> anaylsis, etc) does do a fair to middlin job on large doc sets, and
may
> be the best solution when you have a large corpus of untagged content
> which is not mission critical.

My understanding of what exactly is meant by "natural
language processing" is a bit fuzzy. What's the difference
then between that and the search engines that analyze
content and recommend terms for a taxonomy? E.g.
http://www.iawiki.net/AutomatedClassification

The original question asked was about natural language
search -- where a user enters a question. Is it the same
thing as natural language processing? Does the ability
to handle a user entering a search in the form of a
question mean that the search engine is actually using
natural language processing?