Search code examples
nlpstanford-nlpdependency-parsing

coreNLPDependencyParser output explanation

i am running coreNLPDependencyParser for a sentence

The quick brown fox jumps over the lazy dog.

and i am getting output in this way 

The     DT      4       det
quick   JJ      4       amod
brown   JJ      4       amod
fox     NN      5       nsubj
jumps   VBZ     0       ROOT
over    IN      9       case
the     DT      9       det
lazy    JJ      9       amod
dog     NN      5       nmod
.       .       5       punct

i ran the same input in stanfordDependencyParser and the output is same with different representation

My question is if you see the third column it is giving some score sort of thing, i assumed it to be depth in the tree but its not correct

it is not mentioned anywhere what exactly the score is .

you can see tree here

please enlighten me on output representation?

Solution

  • Each value in the third column is a directed edge in the dependency tree. For example:

    • The head/governor of "quick" is token 4: "fox", and "quick" is a modifier of "fox" (amod)
    • The head/governor of "fox" is token 5: "jumps" and "fox" is the subject of "jumps" (nsubj)

    The value 0 is reserved for the root of the tree, usually the main verb of the sentence.