Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Spacy parser #346

Open
wants to merge 4 commits into
base: master
Choose a base branch
from
Open

Spacy parser #346

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
3909aef
import spacy outside the method
aliqb Aug 31, 2024
44ddbf6
remove unexpected argument
aliqb Aug 31, 2024
af91f04
change tag property name
aliqb Aug 31, 2024
f7f0bd6
handle ez tag
aliqb Aug 31, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 11 additions & 6 deletions hazm/dependency_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,10 @@
from tqdm import tqdm
from typing import List, Tuple
import os
import spacy
from spacy.tokens import Doc
from tqdm import tqdm
from typing import List, Tuple

class MaltParser(NLTKMaltParser):
"""این کلاس شامل توابعی برای شناسایی وابستگی‌های دستوری است.
Expand Down Expand Up @@ -133,7 +137,7 @@ def parse_tagged_sents(
raise Exception("MaltParser parsing failed: %s" % " ".join(cmd))

return (
DependencyGraph(item, top_relation_label='root')
DependencyGraph(item,top_relation_label='root')
for item in open(output_file.name, encoding="utf8").read().split("\n\n") # noqa: SIM115, PTH123
if item.strip()
)
Expand Down Expand Up @@ -318,7 +322,7 @@ def parse_sents(self: MaltParser, sentences: str, verbose: bool = False) -> str:
for sentence in sentences:
self._add_sentence2dict(sentence)

tagged_sentences = self.tagger.tag_sents(sentences,universal_tag=True)
tagged_sentences = self.tagger.tag_sents(sentences)
return self.parse_tagged_sents(tagged_sentences, verbose)


Expand All @@ -332,8 +336,8 @@ def _spacy_to_conll(self,doc):
token.i + 1,
token.text.replace(" ", "_"),
self.lemmatize(token.text, token.pos_).replace(" ", "_"),
token.pos_,
token.pos_,
token.tag_,
token.tag_,
"_",
head_id,
token.dep_,
Expand All @@ -357,12 +361,13 @@ def parse_tagged_sents(self: "SpacyDependencyParser", sentences: List[List[Tuple
for doc_id , doc in enumerate(docs):
pos_tags = [tag for w , tag in sentences[doc_id]]
for i in range(len(doc)):
docs[doc_id][i].pos_ = pos_tags[i]
docs[doc_id][i].pos_ = pos_tags[i].split(',')[0]
docs[doc_id][i].tag_ = pos_tags[i]
conll_sample = self._spacy_to_conll(docs[doc_id])
conll_list.append(conll_sample)

return (
DependencyGraph(item)
DependencyGraph(item, top_relation_label='root')
for item in conll_list
if item.strip()
)
Loading