Hi Min,
sorry for the delayed answer and
thank you to verify the consistency of the kernel description.
The question was
"in your website, in equation K_all(O_1,O_2) as below, it
seems that the loop range of j should be [1,n’] rather than [I,n’]. Is it?
"
You are in right, it is a typo. In the source code the loop range is the one
that you have told. When I was
describing it in the web page I made a mistake.
Cheers
Alessandro
--------------------------------------------------------------
Dr. Alessandro Moschitti
Dept. of Computer Science, Systems and Production
University of Rome Tor Vergata
Via del Politecnico 1,
00133 Rome, Italy
tel +39 06 7259 7333
fax +39 06 72597460
e-mail: moschitti@xxxxxxxxxxxxxxxx
http://ai-nlp.info.uniroma2.it/moschitti/
----- Original Message -----
From: "zhang min" <mzhang@xxxxxxxxxxxxxxxxx>
To: "'Alessandro Moschitti'" <moschitti@xxxxxxxxxxxxxxxx>
Sent: Friday, December 01, 2006 3:07 AM
Subject: RE: [Corpora-List] Software release announcement: Tree Kernels
andmultiple feature vectors in SVM-LIGHT
Hi, Alessandro,
Congratulations for the new tool release with many new features.
I believe the research community will benefit from it.
One small question, in your website, in equation K_all(O_1,O_2) as below,
it
seems that the loop rang of j shoul be [1,n’] rather than [I,n’]. Is it?
Cheers,
Zhang Min
-----Original Message-----
From: owner-corpora@xxxxxxxxxxxx [mailto:owner-corpora@xxxxxxxxxxxx] On
Behalf Of Alessandro Moschitti
Sent: 2006年11月30日 23:24
To: CORPORA@xxxxxx
Subject: [Corpora-List] Software release announcement: Tree Kernels
andmultiple feature vectors in SVM-LIGHT
Dear all,
I have just released the SVM-LIGHT-TK1.2 software. This allows us to
describe a classifying object
using a set of trees and a set of vectors in the input of Support Vector
Machines.
Sets of trees are useful to encode different structured features, e.g. it
is
possible to select
different portions of a parse tree, independently evaluate tree kernels
over
them
and combine the obtained contributions.
Feature Vectors are extremely important to combine different spaces of
manually designed features
and are essential to design SVM models that work on instance pairs
(tuples),
e.g. re-ranking models.
The main software features are listed hereafter:
- Fast Kernel computation.
- Tree forests, i.e. a set of trees over multiple feature spaces can be
specified in the input.
- Vector sets, i.e. multiple feature vectors over multiple feature spaces
can be specified in the input.
- Two types of tree kernels, i.e. subset tree and subtree kernels.
- Embedded combinations of tree and vector-based kernels.
- A commented example on how to design our own kernels.
If you are interested, you can read more about the software and download
it
here:
http://ai-nlp.info.uniroma2.it/moschitti/Tree-Kernel.htm
I appreciate any bug reports, requests and comments.
Best regards,
Alessandro
--------------------------------------------------------------
Dr. Alessandro Moschitti
Dept. of Computer Science, Systems and Production
University of Rome Tor Vergata
Via del Politecnico 1,
00133 Rome, Italy
tel +39 06 7259 7333
fax +39 06 72597460
e-mail: moschitti@xxxxxxxxxxxxxxxx
http://ai-nlp.info.uniroma2.it/moschitti/
