I was wondering whether there is actually a way to extract dependencies between words from the parser. Isn't it the case that internally the parser builds up some lexical dependencies? I guess the class Parse.java is the place to look but it would be great to get some clues as to where to start looking.
Thanks
joa
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi,
Each constituent has a head word. These are based on a set of rules that are encoded in the HeadRules class and a head_rules data file. It should be possible to construct dependencies based on which nodes have which heads however the head rules may not correspond to your (or anyone elses) notion which words are dependent. You can changes the head rules but you'd need to re-train the parser so that it could learn the new lexical dependencies. Hope this helps...Tom
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi,
I was wondering whether there is actually a way to extract dependencies between words from the parser. Isn't it the case that internally the parser builds up some lexical dependencies? I guess the class Parse.java is the place to look but it would be great to get some clues as to where to start looking.
Thanks
joa
Hi,
Each constituent has a head word. These are based on a set of rules that are encoded in the HeadRules class and a head_rules data file. It should be possible to construct dependencies based on which nodes have which heads however the head rules may not correspond to your (or anyone elses) notion which words are dependent. You can changes the head rules but you'd need to re-train the parser so that it could learn the new lexical dependencies. Hope this helps...Tom