I now also committed the second part of this issue. The parser trainer
tool now has an option to specify the Artifact Serializer class which
should be
used for the Head Rules.
With this change it should be possible to train a Spanish parser model
without
any custom code.
Jörn
On 03/22/2014 11:00 AM, Rodrigo Agerri wrote:
Hi Jörn,
This is great, thanks very much, in the email I meant that before thinking
about me contributing something else I had hoped to help solve the casting
issue, but
it has been fixed at lightning speed, so thanks again.
I will try now with the Spanish head rules class I added.
Rodrigo
On 2014/03/21 at 11:37, Joern Kottmann wrote:
On 03/19/2014 02:50 PM, Rodrigo Agerri wrote:
About contributing, sure, no problem I will do that in the future, as soon as
the parser language specific casting is corrected:)
https://issues.apache.org/jira/browse/OPENNLP-665
The casting should work now. I was quite busy the last couple of
days with other stuff.
We still need to improve the command line tool. It should have an
option to take
the impl class name of the head rule files, and there should be a
factory method
which can create the default Head Rule object based on the language.
I hope I will finish that on the weekend.
Jörn
