dmahata commited on
Commit
7680930
1 Parent(s): d0ca0bf

Upload sentence_splitter.py

Browse files
Files changed (1) hide show
  1. sentence_splitter.py +37 -0
sentence_splitter.py ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Copyright 2020 The HuggingFace Team. All rights reserved.
2
+ #
3
+ # Licensed under the Apache License, Version 2.0 (the "License");
4
+ # you may not use this file except in compliance with the License.
5
+ # You may obtain a copy of the License at
6
+ #
7
+ # http://www.apache.org/licenses/LICENSE-2.0
8
+ #
9
+ # Unless required by applicable law or agreed to in writing, software
10
+ # distributed under the License is distributed on an "AS IS" BASIS,
11
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12
+ # See the License for the specific language governing permissions and
13
+ # limitations under the License.
14
+ import re
15
+
16
+ from filelock import FileLock
17
+
18
+
19
+ try:
20
+ import nltk
21
+
22
+ NLTK_AVAILABLE = True
23
+ except (ImportError, ModuleNotFoundError):
24
+ NLTK_AVAILABLE = False
25
+
26
+ if NLTK_AVAILABLE:
27
+ with FileLock(".lock") as lock:
28
+ nltk.download("punkt", quiet=True)
29
+
30
+
31
+ def add_newline_to_end_of_each_sentence(x: str) -> str:
32
+ """This was added to get rougeLsum scores matching published rougeL scores for BART and PEGASUS."""
33
+ re.sub("<n>", "", x) # remove pegasus newline char
34
+ assert (
35
+ NLTK_AVAILABLE
36
+ ), "nltk must be installed to separate newlines between sentences. (pip install nltk)"
37
+ return "\n".join(nltk.sent_tokenize(x))