Creating custom DependencyParser from scratch in Spacy 3 - python-3.x

Question

I am trying to implement my own DependencyParser from scratch in Spacy 3. I create an empty model, create an empty DependencyParser, train it and save its configuration. But when I try to load my custom parser config again, I can only do it successfully if the model is empty. If I am using a non-empty model, then I keep getting this error - ValueError: could not broadcast input array from shape (106,64) into shape (27,64).
import spacy
import random
from spacy.tokens import Doc
from spacy.training import Example
from spacy.pipeline import DependencyParser
from typing import List, Tuple
PARSER_CONFIG = 'parser.cfg'
TRAINING_DATA = [
('find a high paying job with no experience', {
'heads': [0, 4, 4, 4, 0, 7, 7, 4],
'deps': ['ROOT', '-', 'QUALITY', 'QUALITY', 'ACTIVITY', '-', 'QUALITY', 'ATTRIBUTE']
}),
('find good workout classes near home', {
'heads': [0, 3, 3, 0, 5, 3],
'deps': ['ROOT', 'QUALITY', 'QUALITY', 'ACTIVITY', 'QUALITY', 'ATTRIBUTE']
})
]
def create_training_examples(training_data: List[Tuple]) -> List[Example]:
""" Create list of training examples """
examples = []
nlp = spacy.load('en_core_web_md')
for text, annotations in training_data:
print(f"{text} - {annotations}")
examples.append(Example.from_dict(nlp(text), annotations))
return examples
def save_parser_config(parser: DependencyParser):
print(f"Save parser config to '{PARSER_CONFIG}' ... ", end='')
parser.to_disk(PARSER_CONFIG)
print("DONE")
def load_parser_config(parser: DependencyParser):
print(f"Load parser config from '{PARSER_CONFIG}' ... ", end='')
parser.from_disk(PARSER_CONFIG)
print("DONE")
def main():
nlp = spacy.blank('en')
# Create new parser
parser = nlp.add_pipe('parser', first=True)
for text, annotations in TRAINING_DATA:
for label in annotations['deps']:
if label not in parser.labels:
parser.add_label(label)
print(f"Added labels: {parser.labels}")
examples = create_training_examples(TRAINING_DATA)
# Training
# NOTE: The 'lambda: examples' part is mandatory in Spacy 3 - https://spacy.io/usage/v3#migrating-training-python
optimizer = nlp.initialize(lambda: examples)
print(f"Training ... ", end='')
for i in range(25):
print(f"{i} ", end='')
random.shuffle(examples)
nlp.update(examples, sgd=optimizer)
print(f"... DONE")
save_parser_config(parser)
# I can load parser config to blank model ...
nlp = spacy.blank('en')
parser = nlp.add_pipe('parser')
# ... but I cannot load parser config to already existing model
# Return -> ValueError: could not broadcast input array from shape (106,64) into shape (27,64)
# nlp = spacy.load('en_core_web_md')
# parser = nlp.get_pipe('parser')
load_parser_config(parser)
print(f"Current pipeline is {nlp.meta['pipeline']}")
doc = nlp(u'find a high paid job with no degree')
print(f"Arcs: {[(w.text, w.dep_, w.head.text) for w in doc if w.dep_ != '-']}")
if __name__ == '__main__':
main()
The custom parser itself is working as expected. You can test this by commenting out all the code from save_parser_config(parser) to load_parser_config(parser) (inclusive), and run the code again. You will see new labels are assigned as needed. This is why I think the root of the problem is the inability to load the parser configuration of an empty model into a non-empty model. But how to get around this?

Answer 1

I contacted the developers and this is what they answered - https://github.com/explosion/spaCy/discussions/9239