Spacy training own dependency parser heads

1

I am trying to train my own dependency parser , and I am not able to understand what the numbers in the heads list specify. The example is given below

training data

TRAIN_DATA = [ (" They trade mortgage-backed securities.",
{ ‘heads’: [1, 1, 4, 4, 5, 1, 1],
‘deps’: [’ nsubj’, ‘ROOT’, ‘compound’, ‘punct’, ‘nmod’, ‘dobj’, ‘punct’] }),

(" I like London and Berlin.",
{ ‘heads’: [1, 1, 1, 2, 2, 1],

‘deps’: [’ nsubj’, ‘ROOT’, ‘dobj’, ‘cc’, ‘conj’, ‘punct’] }) ]

What do the numbers for heads [1,1,4,4,5,1,1] mean, I have searched the heads all over spacy documentation but couldn’t find an explanation to these numbers.

Can someone help me understand what the numbers mean.

regards

2

Hi! I've explained the concept behind this in more detail here:

Btw, we're trying to keep this forum focused on Prodigy, so for general spaCy-related usage questions, Stack Overflow is a much better place to ask questions :slightly_smiling_face: