last week I sent a mail asking for information about the use of WordNet
in text analysis and I want to thank Mark G Lee, Christian Jacquemin,
Einat Amitay, Manuel J. Maña López, Dan Cristea, and John Arley Burns
for their answers.
However I realize that I didn't explain enough precisely what I'm
looking for. It seems that there was a
misunderstanding on my use of the expression "text analysis" (or
computer assisted text analysis): in my perspective, the simplest
example of "text analysis" is the computation of word concordances.
However
almost all the responses pointed me to references in the field of
Information Retrieval (obviously somehow related but not completely
identical).
In order to make my request clearer it's suitable to spend a few words
about the project I'm involved in. The aim of the project is that of
somehow "analyzing" (take this term in a broad sense) a philosophical
corpus. I was asked to make a list of techniques and tools usually used
in the analysis of corpora. Moreover, as we are currently working at the
construction of an Italian version of Princeton WordNet, we want to pay
a special attention to the possibility of using it in the project.
So I'm looking for uses of WordNet in this kind of text analysis. As
regards the annotation of corpora, I'm aware only of works on semantic
tagging and I would like to know if there can be other uses. Moreover,
as within the project we are thinking of finding concordances of
concepts instead of words, I'm interested in other researches intended
to improve tools for text analysis, providing an additional source of
information.
Many thanks for your kind attention.
All the best
Luisa Bentivogli
-- Luisa Bentivogli - bentivo@irst.itc.it Istituto per la Ricerca Scientifica e Tecnologica Loc. Pante' di Povo I-38050 Trento ITALY Tel: +39-0461-314-574 Fax: +39-0461-302-040 http://ecate.itc.it:1024/