tasksource/AdjectiveScaleProbe-nli

---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: validation
path: data/validation-*
- split: test
path: data/test-*
dataset_info:
features:
- name: premise
dtype: string
- name: hypothesis
dtype: string
- name: label
dtype: string
- name: config
dtype: string
splits:
- name: train
num_bytes: 1673129
num_examples: 15600
- name: validation
num_bytes: 402347
num_examples: 3748
- name: test
num_bytes: 283098
num_examples: 3084
download_size: 0
dataset_size: 2358574
---
# Dataset Card for "AdjectiveScaleProbe-nli"

```bib
@inproceedings{10.1609/aaai.v37i11.26559,
author = {Liu, Wei and Xiang, Ming and Ding, Nai},
title = {Adjective Scale Probe: Can Language Models Encode Formal Semantics Information?},
year = {2023},
isbn = {978-1-57735-880-0},
publisher = {AAAI Press},
url = {https://doi.org/10.1609/aaai.v37i11.26559},
doi = {10.1609/aaai.v37i11.26559},
booktitle = {Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial Intelligence},
articleno = {1490},
numpages = {9},
series = {AAAI'23/IAAI'23/EAAI'23}
}

```

This dataset is designed to investigate whether language models can encode formal semantics information, featuring premise, hypothesis, label, and config, all of which are string types. The dataset is divided into train, validation, and test sets, containing 15600, 3748, and 3084 samples respectively.

原始信息汇总

数据集概述

数据集配置

• 默认配置：
  • 训练集：路径为 data/train-*
  • 验证集：路径为 data/validation-*
  • 测试集：路径为 data/test-*

数据集信息

• 特征：

  • 前提 (premise)：数据类型为 string
  • 假设 (hypothesis)：数据类型为 string
  • 标签 (label)：数据类型为 string
  • 配置 (config)：数据类型为 string

• 数据分割：

  • 训练集 (train)：
    • 字节数：1673129
    • 样本数：15600
  • 验证集 (validation)：
    • 字节数：402347
    • 样本数：3748
  • 测试集 (test)：
    • 字节数：283098
    • 样本数：3084

• 数据集大小：

  • 下载大小：0
  • 数据集大小：2358574