Skip to content

Fix for claims extraction #2

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
cant-access-rediska0123 wants to merge 1 commit into
base: rag_dataset
Choose a base branch
from
Open

Fix for claims extraction #2

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
13 changes: 9 additions & 4 deletions lm-polygraph/src/lm_polygraph/stat_calculators/extract_claims.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -242,11 +242,16 @@ def claims_from_text(self, text: str, tokens: List[int], tokenizer) -> List[Clai
# Iteratively decode tokenized text until decoded sequence length is
# greater or equal to the starting position of current sentence.
# Find sentence location in tokens: tokens[sent_start_token_idx:sent_end_token_idx]
while len(tokenizer.decode(tokens[:sent_start_token_idx])) < sent_start_idx:
# print("while 3")

# while len(tokenizer.decode(tokens[:sent_start_token_idx])) < sent_start_idx:
# # print("while 3")
# sent_start_token_idx += 1
# while len(tokenizer.decode(tokens[:sent_end_token_idx])) < sent_end_idx:
# # print("while 4")
# sent_end_token_idx += 1
while s.replace(' ', '').lower() in tokenizer.decode(tokens[sent_start_token_idx + 1:]).replace(' ', '').lower() and sent_start_token_idx < len(tokens):
sent_start_token_idx += 1
while len(tokenizer.decode(tokens[:sent_end_token_idx])) < sent_end_idx:
# print("while 4")
while s.replace(' ', '').lower() not in tokenizer.decode(tokens[:sent_end_token_idx]).replace(' ', '').lower() and sent_end_token_idx < len(tokens):
sent_end_token_idx += 1

# print("(sent_start_idx, sent_end_idx, sent_start_token_idx, sent_end_token_idx):", (sent_start_idx, sent_end_idx, sent_start_token_idx, sent_end_token_idx))
Expand Down