kinianlo/prlang

---
dataset_info:
- config_name: conceptnet5_vocabulary_en
features:
- name: word
dtype: string
- name: tag
dtype: string
splits:
- name: train
num_bytes: 123167929
num_examples: 6846008
download_size: 45799508
dataset_size: 123167929
- config_name: wiki_20220301_en_nltk_adjectives
features:
- name: adj_id
dtype: uint32
- name: adj
dtype: string
- name: count
dtype: uint64
splits:
- name: train
num_bytes: 39119443
num_examples: 1323576
download_size: 24403987
dataset_size: 39119443
- config_name: wiki_20220301_en_nltk_nouns
features:
- name: noun_id
dtype: uint32
- name: noun
dtype: string
splits:
- name: train
num_bytes: 12442756.0
num_examples: 676770
download_size: 11115529
dataset_size: 12442756.0
- config_name: wiki_20220301_en_nltk_phrases
features:
- name: phrase_id
dtype: uint32
- name: adj_id
dtype: uint32
- name: noun_id
dtype: uint32
- name: count
dtype: uint64
splits:
- name: train
num_bytes: 207602960
num_examples: 10380148
download_size: 129734024
dataset_size: 207602960
- config_name: wiki_20220301_en_nltk_phrases_with_string
features:
- name: phrase_id
dtype: uint32
- name: adj
dtype: string
- name: noun
dtype: string
- name: count
dtype: uint64
splits:
- name: train
num_bytes: 377124084
num_examples: 10380148
download_size: 172157247
dataset_size: 377124084
- config_name: wiki_20220301_en_nltk_uncased_adjectives
features:
- name: adj_id
dtype: uint32
- name: adj
dtype: string
- name: count
dtype: uint64
splits:
- name: train
num_bytes: 36784396
num_examples: 1235601
download_size: 22724468
dataset_size: 36784396
- config_name: wiki_20220301_en_nltk_uncased_nouns
features:
- name: noun_id
dtype: uint32
- name: noun
dtype: string
- name: count
dtype: uint64
splits:
- name: train
num_bytes: 17153952
num_examples: 647524
download_size: 10809791
dataset_size: 17153952
- config_name: wiki_20220301_en_nltk_uncased_phrases
features:
- name: phrase_id
dtype: uint32
- name: adj_id
dtype: uint32
- name: noun_id
dtype: uint32
- name: count
dtype: uint64
splits:
- name: train
num_bytes: 198626820
num_examples: 9931341
download_size: 124034311
dataset_size: 198626820
- config_name: wiki_20220301_en_nltk_uncased_phrases_clean
features:
- name: phrase_id
dtype: uint32
- name: adj_id
dtype: uint32
- name: noun_id
dtype: uint32
- name: count
dtype: uint64
splits:
- name: train
num_bytes: 67986800
num_examples: 3399340
download_size: 41983842
dataset_size: 67986800
- config_name: wiki_20220301_en_nltk_uncased_phrases_with_string
features:
- name: phrase_id
dtype: uint32
- name: adj
dtype: string
- name: noun
dtype: string
- name: count
dtype: uint64
splits:
- name: train
num_bytes: 361160989
num_examples: 9931341
download_size: 164282553
dataset_size: 361160989
- config_name: wiki_20220301_simple_tags_nltk_adjectives
features:
- name: id
dtype: int32
- name: adjective
dtype: string
- name: count
dtype: int64
splits:
- name: train
num_bytes: 508056
num_examples: 21152
download_size: 351437
dataset_size: 508056
- config_name: wiki_20220301_simple_tags_nltk_contexts
features:
- name: noun1_id
dtype: int64
- name: noun2_id
dtype: int64
- name: noun1_bert_id
dtype: int64
- name: noun2_bert_id
dtype: int64
- name: adjective1_id
dtype: int64
- name: adjective2_id
dtype: int64
- name: schema_id
dtype: int64
- name: sentence
dtype: string
- name: mask_position
dtype: int64
splits:
- name: train
num_bytes: 5162738640
num_examples: 34644320
download_size: 562170983
dataset_size: 5162738640
- config_name: wiki_20220301_simple_tags_nltk_contexts_epsilon
features:
- name: noun1_id
dtype: int64
- name: noun2_id
dtype: int64
- name: adjective1_id
dtype: int64
- name: adjective2_id
dtype: int64
- name: schema_id
dtype: int64
- name: epsilon
dtype: float64
splits:
- name: train
num_bytes: 1662927360
num_examples: 34644320
download_size: 342106520
dataset_size: 1662927360
- config_name: wiki_20220301_simple_tags_nltk_contexts_epsilon_no_intro
features:
- name: noun1_id
dtype: int64
- name: noun2_id
dtype: int64
- name: adjective1_id
dtype: int64
- name: adjective2_id
dtype: int64
- name: schema_id
dtype: int64
- name: epsilon
dtype: float64
splits:
- name: train
num_bytes: 1662927360
num_examples: 34644320
download_size: 337961367
dataset_size: 1662927360
- config_name: wiki_20220301_simple_tags_nltk_contexts_no_intro
features:
- name: noun1_id
dtype: int64
- name: noun2_id
dtype: int64
- name: noun1_bert_id
dtype: int64
- name: noun2_bert_id
dtype: int64
- name: adjective1_id
dtype: int64
- name: adjective2_id
dtype: int64
- name: schema_id
dtype: int64
- name: sentence
dtype: string
- name: mask_position
dtype: int64
splits:
- name: train
num_bytes: 4022762320
num_examples: 34644320
download_size: 285243023
dataset_size: 4022762320
- config_name: wiki_20220301_simple_tags_nltk_filtered_noun_pairs
features:
- name: noun1_id
dtype: int64
- name: noun2_id
dtype: int64
- name: adjectives_id
sequence: int64
splits:
- name: train
num_bytes: 25983240
num_examples: 433054
download_size: 4499602
dataset_size: 25983240
- config_name: wiki_20220301_simple_tags_nltk_noun_pairs
features:
- name: noun1_id
dtype: int32
- name: noun2_id
dtype: int32
- name: adjectives_id
sequence: int32
splits:
- name: train
num_bytes: 125583432
num_examples: 3245260
download_size: 44230314
dataset_size: 125583432
- config_name: wiki_20220301_simple_tags_nltk_nouns
features:
- name: id
dtype: int32
- name: noun
dtype: string
- name: count
dtype: int64
splits:
- name: train
num_bytes: 221774
num_examples: 9521
download_size: 154872
dataset_size: 221774
- config_name: wiki_20220301_simple_tags_nltk_phrases
features:
- name: adjective_id
dtype: int32
- name: noun_id
dtype: int32
- name: count
dtype: int64
splits:
- name: train
num_bytes: 3514128
num_examples: 219633
download_size: 1993091
dataset_size: 3514128
- config_name: wiki_20220301_simple_tags_nltk_scenarios
features:
- name: noun1_id
dtype: uint32
- name: noun2_id
dtype: uint32
- name: adjectives_id
sequence: uint32
- name: epsilons
sequence: float64
splits:
- name: train
num_bytes: 2702256960
num_examples: 51966480
download_size: 553286399
dataset_size: 2702256960
- config_name: wiki_20220301_simple_tags_nltk_scenarios_epsilon
features:
- name: noun1_id
dtype: int64
- name: noun2_id
dtype: int64
- name: adjectives_id
sequence: int64
- name: epsilons
sequence: float64
- name: adjectives_entropy
dtype: float64
splits:
- name: train
num_bytes: 4157318400
num_examples: 51966480
download_size: 0
dataset_size: 4157318400
configs:
- config_name: conceptnet5_vocabulary_en
data_files:
- split: train
path: conceptnet5_vocabulary_en/train-*
- config_name: wiki_20220301_en_nltk_adjectives
data_files:
- split: train
path: wiki_20220301_en_nltk_adjectives/train-*
- config_name: wiki_20220301_en_nltk_nouns
data_files:
- split: train
path: wiki_20220301_en_nltk_nouns/train-*
- config_name: wiki_20220301_en_nltk_phrases
data_files:
- split: train
path: wiki_20220301_en_nltk_phrases/train-*
- config_name: wiki_20220301_en_nltk_phrases_with_string
data_files:
- split: train
path: wiki_20220301_en_nltk_phrases_with_string/train-*
- config_name: wiki_20220301_en_nltk_uncased_adjectives
data_files:
- split: train
path: wiki_20220301_en_nltk_uncased_adjectives/train-*
- config_name: wiki_20220301_en_nltk_uncased_nouns
data_files:
- split: train
path: wiki_20220301_en_nltk_uncased_nouns/train-*
- config_name: wiki_20220301_en_nltk_uncased_phrases
data_files:
- split: train
path: wiki_20220301_en_nltk_uncased_phrases/train-*
- config_name: wiki_20220301_en_nltk_uncased_phrases_clean
data_files:
- split: train
path: wiki_20220301_en_nltk_uncased_phrases_clean/train-*
- config_name: wiki_20220301_en_nltk_uncased_phrases_with_string
data_files:
- split: train
path: wiki_20220301_en_nltk_uncased_phrases_with_string/train-*
- config_name: wiki_20220301_simple_tags_nltk_adjectives
data_files:
- split: train
path: wiki_20220301_simple_tags_nltk_adjectives/train-*
- config_name: wiki_20220301_simple_tags_nltk_contexts
data_files:
- split: train
path: wiki_20220301_simple_tags_nltk_contexts/train-*
- config_name: wiki_20220301_simple_tags_nltk_contexts_epsilon
data_files:
- split: train
path: wiki_20220301_simple_tags_nltk_contexts_epsilon/train-*
- config_name: wiki_20220301_simple_tags_nltk_contexts_epsilon_no_intro
data_files:
- split: train
path: wiki_20220301_simple_tags_nltk_contexts_epsilon_no_intro/train-*
- config_name: wiki_20220301_simple_tags_nltk_contexts_no_intro
data_files:
- split: train
path: wiki_20220301_simple_tags_nltk_contexts_no_intro/train-*
- config_name: wiki_20220301_simple_tags_nltk_filtered_noun_pairs
data_files:
- split: train
path: wiki_20220301_simple_tags_nltk_filtered_noun_pairs/train-*
- config_name: wiki_20220301_simple_tags_nltk_noun_pairs
data_files:
- split: train
path: wiki_20220301_simple_tags_nltk_noun_pairs/train-*
- config_name: wiki_20220301_simple_tags_nltk_nouns
data_files:
- split: train
path: wiki_20220301_simple_tags_nltk_nouns/train-*
- config_name: wiki_20220301_simple_tags_nltk_phrases
data_files:
- split: train
path: wiki_20220301_simple_tags_nltk_phrases/train-*
- config_name: wiki_20220301_simple_tags_nltk_scenarios
data_files:
- split: train
path: wiki_20220301_simple_tags_nltk_scenarios/train-*
- config_name: wiki_20220301_simple_tags_nltk_scenarios_epsilon
data_files:
- split: train
path: wiki_20220301_simple_tags_nltk_scenarios_epsilon/train-*
---
# Dataset Card for "prlang"

[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

原始信息汇总

数据集概述

数据集配置

conceptnet5_vocabulary_en

• 特征:
  • word: 字符串
  • tag: 字符串
• 分割:
  • train:
    • 字节数: 123167929
    • 样本数: 6846008
• 下载大小: 45799508
• 数据集大小: 123167929

wiki_20220301_en_nltk_adjectives

• 特征:
  • adj_id: 无符号32位整数
  • adj: 字符串
  • count: 无符号64位整数
• 分割:
  • train:
    • 字节数: 39119443
    • 样本数: 1323576
• 下载大小: 24403987
• 数据集大小: 39119443

wiki_20220301_en_nltk_nouns

• 特征:
  • noun_id: 无符号32位整数
  • noun: 字符串
• 分割:
  • train:
    • 字节数: 12442756.0
    • 样本数: 676770
• 下载大小: 11115529
• 数据集大小: 12442756.0

wiki_20220301_en_nltk_phrases

• 特征:
  • phrase_id: 无符号32位整数
  • adj_id: 无符号32位整数
  • noun_id: 无符号32位整数
  • count: 无符号64位整数
• 分割:
  • train:
    • 字节数: 207602960
    • 样本数: 10380148
• 下载大小: 129734024
• 数据集大小: 207602960

wiki_20220301_en_nltk_phrases_with_string

• 特征:
  • phrase_id: 无符号32位整数
  • adj: 字符串
  • noun: 字符串
  • count: 无符号64位整数
• 分割:
  • train:
    • 字节数: 377124084
    • 样本数: 10380148
• 下载大小: 172157247
• 数据集大小: 377124084

wiki_20220301_en_nltk_uncased_adjectives

• 特征:
  • adj_id: 无符号32位整数
  • adj: 字符串
  • count: 无符号64位整数
• 分割:
  • train:
    • 字节数: 36784396
    • 样本数: 1235601
• 下载大小: 22724468
• 数据集大小: 36784396

wiki_20220301_en_nltk_uncased_nouns

• 特征:
  • noun_id: 无符号32位整数
  • noun: 字符串
  • count: 无符号64位整数
• 分割:
  • train:
    • 字节数: 17153952
    • 样本数: 647524
• 下载大小: 10809791
• 数据集大小: 17153952

wiki_20220301_en_nltk_uncased_phrases

• 特征:
  • phrase_id: 无符号32位整数
  • adj_id: 无符号32位整数
  • noun_id: 无符号32位整数
  • count: 无符号64位整数
• 分割:
  • train:
    • 字节数: 198626820
    • 样本数: 9931341
• 下载大小: 124034311
• 数据集大小: 198626820

wiki_20220301_en_nltk_uncased_phrases_clean

• 特征:
  • phrase_id: 无符号32位整数
  • adj_id: 无符号32位整数
  • noun_id: 无符号32位整数
  • count: 无符号64位整数
• 分割:
  • train:
    • 字节数: 67986800
    • 样本数: 3399340
• 下载大小: 41983842
• 数据集大小: 67986800

wiki_20220301_en_nltk_uncased_phrases_with_string

• 特征:
  • phrase_id: 无符号32位整数
  • adj: 字符串
  • noun: 字符串
  • count: 无符号64位整数
• 分割:
  • train:
    • 字节数: 361160989
    • 样本数: 9931341
• 下载大小: 164282553
• 数据集大小: 361160989

wiki_20220301_simple_tags_nltk_adjectives

• 特征:
  • id: 32位整数
  • adjective: 字符串
  • count: 64位整数
• 分割:
  • train:
    • 字节数: 508056
    • 样本数: 21152
• 下载大小: 351437
• 数据集大小: 508056

wiki_20220301_simple_tags_nltk_contexts

• 特征:
  • noun1_id: 64位整数
  • noun2_id: 64位整数
  • noun1_bert_id: 64位整数
  • noun2_bert_id: 64位整数
  • adjective1_id: 64位整数
  • adjective2_id: 64位整数
  • schema_id: 64位整数
  • sentence: 字符串
  • mask_position: 64位整数
• 分割:
  • train:
    • 字节数: 5162738640
    • 样本数: 34644320
• 下载大小: 562170983
• 数据集大小: 5162738640

wiki_20220301_simple_tags_nltk_contexts_epsilon

• 特征:
  • noun1_id: 64位整数
  • noun2_id: 64位整数
  • adjective1_id: 64位整数
  • adjective2_id: 64位整数
  • schema_id: 64位整数
  • epsilon: 64位浮点数
• 分割:
  • train:
    • 字节数: 1662927360
    • 样本数: 34644320
• 下载大小: 342106520
• 数据集大小: 1662927360

wiki_20220301_simple_tags_nltk_contexts_epsilon_no_intro

• 特征:
  • noun1_id: 64位整数
  • noun2_id: 64位整数
  • adjective1_id: 64位整数
  • adjective2_id: 64位整数
  • schema_id: 64位整数
  • epsilon: 64位浮点数
• 分割:
  • train:
    • 字节数: 1662927360
    • 样本数: 34644320
• 下载大小: 337961367
• 数据集大小: 1662927360

wiki_20220301_simple_tags_nltk_contexts_no_intro

• 特征:
  • noun1_id: 64位整数
  • noun2_id: 64位整数
  • noun1_bert_id: 64位整数
  • noun2_bert_id: 64位整数
  • adjective1_id: 64位整数
  • adjective2_id: 64位整数
  • schema_id: 64位整数
  • sentence: 字符串
  • mask_position: 64位整数
• 分割:
  • train:
    • 字节数: 4022762320
    • 样本数: 34644320
• 下载大小: 285243023
• 数据集大小: 4022762320

wiki_20220301_simple_tags_nltk_filtered_noun_pairs

• 特征:
  • noun1_id: 64位整数
  • noun2_id: 64位整数
  • adjectives_id: 64位整数序列
• 分割:
  • train:
    • 字节数: 25983240
    • 样本数: 433054
• 下载大小: 4499602
• 数据集大小: 25983240

wiki_20220301_simple_tags_nltk_noun_pairs

• 特征:
  • noun1_id: 32位整数
  • noun2_id: 32位整数
  • adjectives_id: 32位整数序列
• 分割:
  • train:
    • 字节数: 125583432
    • 样本数: 3245260
• 下载大小: 44230314
• 数据集大小: 125583432

wiki_20220301_simple_tags_nltk_nouns

• 特征:
  • id: 32位整数
  • noun: 字符串
  • count: 64位整数
• 分割:
  • train:
    • 字节数: 221774
    • 样本数: 9521
• 下载大小: 154872
• 数据集大小: 221774

wiki_20220301_simple_tags_nltk_phrases

• 特征:
  • adjective_id: 32位整数
  • noun_id: 32位整数
  • count: 64位整数
• 分割:
  • train:
    • 字节数: 3514128
    • 样本数: 219633
• 下载大小: 1993091
• 数据集大小: 3514128

wiki_20220301_simple_tags_nltk_scenarios

• 特征:
  • noun1_id: 无符号32位整数
  • noun2_id: 无符号32位整数
  • adjectives_id: 无符号32位整数序列
  • epsilons: 64位浮点数序列
• 分割:
  • train:
    • 字节数: 2702256960
    • 样本数: 51966480
• 下载大小: 553286399
• 数据集大小: 2702256960

wiki_20220301_simple_tags_nltk_scenarios_epsilon

• 特征:
  • noun1_id: 64位整数
  • noun2_id: 64位整数
  • adjectives_id: 64位整数序列
  • epsilons: 64位浮点数序列
  • adjectives_entropy: 64位浮点数
• 分割:
  • train:
    • 字节数: 4157318400
    • 样本数: 51966480
• 下载大小: 0
• 数据集大小: 4157318400