tasksource/idioms-nli

---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: test
path: data/test-*
dataset_info:
features:
- name: premise
dtype: string
- name: hypothesis
dtype: string
- name: label
dtype: string
splits:
- name: train
num_bytes: 5625758
num_examples: 20369
- name: test
num_bytes: 924064
num_examples: 3350
download_size: 3748392
dataset_size: 6549822
---
# Dataset Card for "idioms-nli"

https://github.com/an-eve/nlp-nli-idioms/

```
@inproceedings{stowe-2022,
title = "IMPLI: Investigating NLI Models' Performance on Figurative Language",
author = "Stowe, Kevin and Utama, Prasetya Ajie, and Gurevytch, Iryna",
booktitle = "Proceedings of the 2022 Conference for the Association of Computational Linguistics",
month = "06",
year = "2022",
publisher = "Association for Computational Linguistics",
url = "tbd",
}
```

原始信息汇总

数据集概述

数据集名称

• 名称：idioms-nli

数据集配置

• 默认配置 (config_name: default)
  • 训练数据 (split: train)：路径 data/train-*
  • 测试数据 (split: test)：路径 data/test-*

数据集特征

• 特征名称：premise
  • 数据类型：string
• 特征名称：hypothesis
  • 数据类型：string
• 特征名称：label
  • 数据类型：string

数据集分割

• 训练集 (name: train)
  • 数据量：5625758字节
  • 示例数量：20369
• 测试集 (name: test)
  • 数据量：924064字节
  • 示例数量：3350

数据集大小

• 下载大小：3748392字节
• 数据集总大小：6549822字节