def benchmark_stanza_mdl():
nlp = stanza.Pipeline('da',
processors='tokenize,pos,lemma,depparse',
tokenize_pretokenized=True)
start = time.time()
deps_pred = []
for sent in sentences_tokens:
doc = nlp(" ".join(sent))
deprels = []
depheads = []
for tok in doc.iter_tokens():
deprels.append(tok.words[0].deprel)
depheads.append(tok.words[0].head)
deps_pred.append([(r, h) for r, h in zip(deprels, depheads)])
print('**Stanza model**')
print_speed_performance(start, num_sentences, num_tokens)
assert len(deps_pred) == num_sentences
assert sum([len(s) for s in deps_pred]) == num_tokens
print(dependency_report(deps_true, deps_pred))
def benchmark_spacy_mdl():
def normalize_spacy_head(i, hd):
return 0 if i == hd else hd + 1
nlp = load_spacy_model()
parser = nlp.parser
start = time.time()
deps_pred = []
for sent in sentences_tokens:
doc = nlp.tokenizer.tokens_from_list(sent)
doc = parser(doc)
deprels = []
depheads = []
for i, tok in enumerate(doc):
deprels.append(tok.dep_.lower())
depheads.append(normalize_spacy_head(i, tok.head.i))
deps_pred.append([(r, h) for r, h in zip(deprels, depheads)])
print('**Spacy model**')
print_speed_performance(start, num_sentences, num_tokens)
assert len(deps_pred) == num_sentences
assert sum([len(s) for s in deps_pred]) == num_tokens
print(dependency_report(deps_true, deps_pred))
def benchmark_dacy_mdl(dacy_model="da_dacy_large_tft-0.0.0"):
"""
an adaption of benchmark spacy model which is compatible with spacy v. 3
running this requires:
spacy >= 3.0.0
spacy-transformers
"""
def normalize_spacy_head(i, hd):
return 0 if i == hd else hd+1
from spacy.tokens import Doc
import dacy
nlp = dacy.load(dacy_model)
trf = nlp.get_pipe('transformer')
parser = nlp.get_pipe('parser')
start = time.time()
deps_pred = []
for sent in sentences_tokens:
doc = Doc(nlp.vocab, words=sent)
doc = trf(doc)
doc = parser(doc)
deprels = []
depheads = []
for i, tok in enumerate(doc):
deprels.append(tok.dep_.lower())
depheads.append(normalize_spacy_head(i, tok.head.i))
deps_pred.append([(r,h) for r,h in zip(deprels, depheads)])
print('**Spacy model**')
print_speed_performance(start, num_sentences, num_tokens)
assert len(deps_pred)==num_sentences
assert sum([len(s) for s in deps_pred])==num_tokens
print(dependency_report(deps_true, deps_pred))