# Copyright 2020 The HuggingFace Datasets Authors and the current dataset script contributor.
#
# 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.
"""LogiQA dataset."""
importdatasets
importjson
importast
_CITATION="""\
@ARTICLE{10174688,
author={Liu, Hanmeng and Liu, Jian and Cui, Leyang and Teng, Zhiyang and Duan, Nan and Zhou, Ming and Zhang, Yue},
journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
title={LogiQA 2.0 — An Improved Dataset for Logical Reasoning in Natural Language Understanding},
year={2023},
volume={},
number={},
pages={1-16},
doi={10.1109/TASLP.2023.3293046}}
"""
_DESCRIPTION="""\
The dataset is an amendment and re-annotation of LogiQA in 2020, a large-scale logical reasoning reading comprehension dataset adapted from the Chinese Civil Service Examination. We increase the data size, refine the texts with manual translation by professionals, and improve the quality by removing items with distinctive cultural features like Chinese idioms. Furthermore, we conduct a fine-grained annotation on the dataset and turn it into a two-way natural language inference (NLI) task, resulting in 35k premise-hypothesis pairs with gold labels, making it the first large-scale NLI dataset for complex logical reasoning
