Jean,
Interesting, your concordancer allows me to confirm that the European
Constitution has no "intelligence", no "common sense", but a few
uses of "sex"...
BUT does anyone know of a tool which can read in a corpus
and then answer questions about the semantic content of the text?
Bayan Abu Shawar here at Leeds has FAQchat, which can read in
a Frequently-Asked Questions corpus and then generates a chatbot which
can answer general English questions with answers from the FAQ;
but this only works with an informative text structred as a set of
typical questions with answers. Does anyone have a tool/method
to transform any informative text (eg the European Constitution,
assuming a generous interpretation of "informative") into an FAQ,
or into a natrual-language query-answerer?
eric atwell, Leeds University
On Tue, 12 Apr 2005, Jean Veronis wrote:
> Dear all,
>
> As you probably heard even if you are not a EU citizen, the brand new
> European Constitution is a lengthy, almost unreadable piece of Eurojargon :
> 482 pages, 1 million characters. Not for the average citizen (but he/she will
> have to vote about it soon).
>
> http://aixtal.blogspot.com/2005/04/text-navigate-through-european.html
>
> In order to help understanding this document, I have written an on-line
> concordancer for the English and French versions. This could be useful to
> you, and it could be a source of interesting exercises on regular expressions
> for your students.
>
> Have fun.
>
> --jv
> http://aixtal.blogspot.com
>
>
>
>
>
>
-- Eric Atwell, Senior Lecturer, Computer Vision and Language research group, School of Computing, University of Leeds, LEEDS LS2 9JT, England TEL: +44-113-2335430 FAX: +44-113-2335468 http://www.comp.leeds.ac.uk/eric
This archive was generated by hypermail 2b29 : Wed Apr 13 2005 - 10:53:12 MET DST