Correct info extracted from source documents

I am using VB6 and XSLT1.0, XML1.0 and SQL Server MSDE

I am designing a system that takes sections from
different document formats and converts it to XML. I
am crudely transforming these docs to XML and then
using XSLT to provide a load of rules to transform
into a well formed XML document.

The problem:
The user needs to know if this data has been correctly
extracted from the source documents.  I am having to
take a number of assumptions on the format of the
documents but as they are created by users they are
prone to human error.  How can I report back to the
user that the info has been correctly extracted from
the data? How would I be able to know if it has taken
all of the information, has it missed some of the data
as the user used the incorrect format? (i think I
would struggle with this one!)

Something at the back of my head is shouting XML
schemas but I am new to the XML game and not sure how
you would report this information back to the user.

Any help or experience would be gratefully received.

__________________________________________________
Do You Yahoo!?
Tired of spam?  Yahoo! Mail has the best spam protection around 
http://mail.yahoo.com