transformers/examples/legacy/seq2seq/sentence_splitter.py
Suraj Patil 1c8c2d9ab3
[WIP][examples/seq2seq] move old s2s scripts to legacy (#10136)
* move old s2s scripts to legacy

* add the tests back

* proper rename

* restore

* Apply suggestions from code review

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

Co-authored-by: Stas Bekman <stas@stason.org>
Co-authored-by: Stas Bekman <stas00@users.noreply.github.com>
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
2021-02-15 10:48:02 -08:00

36 lines
1.2 KiB
Python

# Copyright 2020 The HuggingFace Team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import re
from filelock import FileLock
try:
import nltk
NLTK_AVAILABLE = True
except (ImportError, ModuleNotFoundError):
NLTK_AVAILABLE = False
if NLTK_AVAILABLE:
with FileLock(".lock") as lock:
nltk.download("punkt", quiet=True)
def add_newline_to_end_of_each_sentence(x: str) -> str:
"""This was added to get rougeLsum scores matching published rougeL scores for BART and PEGASUS."""
re.sub("<n>", "", x) # remove pegasus newline char
assert NLTK_AVAILABLE, "nltk must be installed to separate newlines between sentences. (pip install nltk)"
return "\n".join(nltk.sent_tokenize(x))