Skip to content

bugfix: mentions in wiki table getting missed #108

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

Open
mayankmusaddi wants to merge 2 commits into
base: main
Choose a base branch
from
Open

bugfix: mentions in wiki table getting missed #108

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8015712
bugfix: mentions in wiki table getting missed
mayankmusaddi Sep 14, 2022
4ebdefe
bugfix: errors due to mismatch in doc_name
mayankmusaddi Sep 14, 2022
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
21 changes: 17 additions & 4 deletions REL/generate_train_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,8 +74,17 @@ def process_wned(self, dataset):

contents = {}
exist_doc_names = []
cnt_replaced = 0
for doc in root:
doc_name = doc.attrib["docName"].replace("&", "&")

# Replacement in string to makeup for mismatch in doc_names present in annotations_xml and generic folder
doc_name = doc_name.replace("'","_").replace("É","Р").replace("í","б").replace(
"_&_","___").replace("ü","Б").replace("â","Г").replace("ö","Ф").replace(
"é","В").replace("ó","в")
if doc_name.endswith("."):
doc_name = doc_name[:-1]+"_"

if doc_name in exist_doc_names:
print(
"Duplicate document found, will be removed later in the process: {}".format(
Expand All @@ -87,13 +96,17 @@ def process_wned(self, dataset):
doc_path = os.path.join(
self.wned_path, "{}/RawText/{}".format(dataset, doc_name)
)
with open(doc_path, "r", encoding="utf-8") as cf:
doc_text = " ".join(cf.readlines())
cf.close()

try:
with open(doc_path, "r", encoding="utf-8") as cf:
doc_text = " ".join(cf.readlines())
except:
print("Couldn't find: ", doc_path)
continue

doc_text = doc_text.replace("&", "&")
split_text = re.split(r"{}".format(split), doc_text)

cnt_replaced = 0
sentences = {}
mentions_gt = {}
total_gt = 0
Expand Down
6 changes: 3 additions & 3 deletions REL/wikipedia_yago_freq.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -236,9 +236,6 @@ def __wiki_counts(self):

print("Calculating Wikipedia mention/entity occurrences")

last_processed_id = -1
exist_id_found = False

wiki_anchor_files = os.listdir(
os.path.join(self.base_url, self.wiki_version, "basic_data/anchor_files/")
)
Expand All @@ -249,6 +246,9 @@ def __wiki_counts(self):
"basic_data/anchor_files/",
wiki_anchor,
)

last_processed_id = -1
exist_id_found = False

with open(wiki_file, "r", encoding="utf-8") as f:
for line in f:
Expand Down