Hello,
i am currently working on my thesis in information processing in the
humanities.
i am developping an extension for lucene, that integrates the user´s
query history into the retrieval process.
i want to implement a neural network, that adapts to the users
information need.
first, the application performs a full-text search on a metadata corpus.
q1: how can i modify the format of lucenes output, for example, adding
the ranking value.
the user then selects the apparently most interesting documents (by it
dc metadata). this second user-input should be used to adapt the neural
network weights.
q2: is it possible to
a: reuse / generate a lucene term-document-matrix and
b: initialize the synapses of a nn with that matrix
c: does lucene provide any interface at that level of the
information extraction process
until now, i am not entirely decided which neural network api i should
use. joone, at a first glance, seems to be quite user friendly but
integrate it into one´s own applications doesn´t, so that a more
"customizeable" solution is needed.
thank you for any hint!
thomas krämer
university of cologne, germany
---------------------------------------------------------------------
To unsubscribe, e-mail: lucene-user-unsubscribe@jakarta.apache.org
For additional commands, e-mail: lucene-user-help@jakarta.apache.org
|