Quoting from >>> csh3 <[log in to unmask]> 17/08/2010 11:09 >>>
"The second area where a standard structure to reports may be prescient is in the use of technologies to create meaningful rich indices to grey literature, thereby reducing the need for manual input. We have recently undertaken a R&D project looking the use of Natural Language Processing (NLP) to index grey literature and the results have been promising. For those of us who have a limited handle on technology this means that the computer programme trawls through digital versions of the grey lit records (in volume) and extracts indexing information in an ‘intelligent way’. The computer learns that, for example when it comes across the phrase ‘Church Lane’ it indexes this under location information rather than monument type because the word Church is suffixed by Lane. Similarly though the position of information in the report is important for meaningful indexing using NLP; we can teach the programme to give greater importance to location information in the title rather than the body of the text so that if in the grey lit report the author is comparing the finds from two different sites in the text that particular report is not incorrectly indexed under the site used for comparison. So you can see that if you want to use NLP technology to index grey lit (perhaps especially important for indexing scans of grey lit) then the structure (standards) within the report is quite important. But that’s a big if."
WARNING
Any opinions or statements expressed in this e-mail are those of the individual and not necessarily those of North Yorkshire County Council.
This e-mail and any files transmitted with it are confidential and solely for the use of the intended recipient. If you receive this in error, please do not disclose any information to anyone, notify the sender at the above address and then destroy all copies.
North Yorkshire County Council’s
computer systems and communications may be monitored to ensure effective
operation of the system and for other lawful purposes. All GCSX traffic may be
subject to recording and/or monitoring in accordance with relevant
legislation.
Although we have endeavoured to ensure that this e-mail and any attachments are free from any virus we would advise you to take any necessary steps to ensure that they are actually virus free.
If you receive an automatic response
stating that the recipient is away from the office and you wish to request
information under either the Freedom of Information Act, the Data Protection Act
or the Environmental Information Regulations please forward your request by
e-mail to the Data Management Team ([log in to unmask])
who will process your request.
North Yorkshire County
Council.