Hello, We are interested in OpenNLP's parser tool as well. To generate models, we need to convert data to the Penn-format the Parser training tool understands. This is doable. But the trainer also wants a headRules file, which for English i found [1]. The contents if the head rules file is not explained in the manual (TODO: Add documentation about the head rules file).
I see numbers and POS-tags. But that is all i can tell. When doing the data format conversion, what information must be write to our head rules file? Also, our source data does not use UD or Penn-treebank type POS-tags. I do not assume this is a problem for the trainer tool, but is it? Many thanks, Markus [1] http://opennlp.sourceforge.net/models/english/parser/head_rules
