Models: SyntaxNet : echo "i am human" | syntaxnet/demo.sh

[dsindex]

using parsey_mcparseface model :

$ echo "i am human" | syntaxnet/demo.sh
Input: i am human
Parse:
human JJ ROOT
+-- i PRP nsubj
+-- am VBP cop

$ echo "i am a student" | syntaxnet/demo.sh
Input: i am a student
Parse:
student NN ROOT
+-- i PRP nsubj
+-- am VBP cop
+-- a DT det

this model seems to be weak for 'be' verb. why?
is this model not the one described in the paper( http://www.petrovi.de/data/acl15.pdf )?

[slavpetrov]

These parses are correct as the Stanford dependencies treat the copula as the dependent rather than the root. Quoting from the manual:

4.7 The treatment of copula verbs
The design philosophy of SD has been to maximize dependencies between content words, and so we
normally regard a copula verb like be as an auxiliary modifier, even when its complement is an adjective
or predicative noun (see the references in section 6 for more discussion and motivation). However, some
people do not like this because then the head of some sentences is no longer a verb. In the dependency
conversion software, you can ask for the copula to remain the head when its complement is an adjective
or noun by giving the flag -makeCopulaHead. Uses of the verb be as in auxiliary in passives and
progressives will still be treated as a non-head auxiliary.
http://nlp.stanford.edu/software/dependencies_manual.pdf

Marking as closed, but feel free to reopen if something is unclear.

[dsindex]

thank you! i got it :)

[mastasky]

@slavpetrov: Can this be changed in Parsey by using a flag as well?