I'd agree - I suspect that simply matching terms doesn't help that much
- we'd need to know the context of it, but then it all gets very sticky.
There is some work on mining the Chemistry literature from Cambridge
(UK) - using ? OSCAR/ Sci-ML I think....
We've done a little work in the clinical domain using structured
abstracts as a guide to help extract info automatically/
semi-automatically. Looks promising, but noting concrete yet.
Matt
Colin Batchelor wrote:
I also think that the machine-readable representation of facts about
biology
should have a higher priortiy than the description of experimental
setups
and procedures (which is the major goal of OBI and EXPO). People only
have
limited time and motivation to create machine-readable annotations,
and it
is much more useful when they spend that time on describing the
RESULTS
(biological facts). Of course, descriptions of experiments are also
valuable, when there are sufficient resources left for creating them.
Good point. What I was sort of driving at (and failing) was the context
in which the facts are mentioned---are they the aim of the paper,
background information, mentioned as results and so forth?
Currently in our (Project Prospect) RSS feeds we connect the OBO terms
to the article with the content module of RSS, which I feel is
unsatisfactory.
Best wishes,
Colin.
--
http://acl.icnet.uk/~mw
http://adhominem.blogsome.com/
+44 (0)7834 899570
