Skip to content

Commit fed6e92

Browse files
author
The TensorFlow Datasets Authors
committed
Automated metadata update.
PiperOrigin-RevId: 797302143
1 parent cae85a2 commit fed6e92

File tree

3 files changed

+83
-1
lines changed

3 files changed

+83
-1
lines changed
Lines changed: 67 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,67 @@
1+
{
2+
"citation": "@misc{alex2019multinews,\n title={Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model},\n author={Alexander R. Fabbri and Irene Li and Tianwei She and Suyi Li and Dragomir R. Radev},\n year={2019},\n eprint={1906.01749},\n archivePrefix={arXiv},\n primaryClass={cs.CL}\n}",
3+
"description": "# Multi-News Dataset\n\nMulti-News consists of news articles and human-written summaries of these\narticles from the news site `newser.com`. Each summary is professionally written\nby editors and includes links to the original articles cited.\n\nThis is the first large-scale dataset for multi-document summarization on news\narticles.\n\nEach record has two features:\n\n* `document`: Texts of news articles, separated by special token \"|||||\".\n* `summary`: Summary of the news.",
4+
"downloadSize": "756785627",
5+
"fileFormat": "array_record",
6+
"location": {
7+
"urls": [
8+
"https://github.com/Alex-Fabbri/Multi-News"
9+
]
10+
},
11+
"moduleName": "tensorflow_datasets.datasets.multi_news.multi_news_dataset_builder",
12+
"name": "multi_news",
13+
"redistributionInfo": {
14+
"license": "For non-commercial research and educational purposes only"
15+
},
16+
"releaseNotes": {
17+
"1.0.0": "Initial release.",
18+
"2.0.0": "Update the dataset with valid URLs.",
19+
"2.1.0": "Update the dataset with cleaned URLs."
20+
},
21+
"splits": [
22+
{
23+
"filepathTemplate": "{DATASET}-{SPLIT}.{FILEFORMAT}-{SHARD_X_OF_Y}",
24+
"name": "train",
25+
"numBytes": "560139736",
26+
"shardLengths": [
27+
"5622",
28+
"5621",
29+
"5621",
30+
"5622",
31+
"5622",
32+
"5621",
33+
"5621",
34+
"5622"
35+
]
36+
},
37+
{
38+
"filepathTemplate": "{DATASET}-{SPLIT}.{FILEFORMAT}-{SHARD_X_OF_Y}",
39+
"name": "validation",
40+
"numBytes": "68490592",
41+
"shardLengths": [
42+
"5622"
43+
]
44+
},
45+
{
46+
"filepathTemplate": "{DATASET}-{SPLIT}.{FILEFORMAT}-{SHARD_X_OF_Y}",
47+
"name": "test",
48+
"numBytes": "70250301",
49+
"shardLengths": [
50+
"5622"
51+
]
52+
}
53+
],
54+
"supervisedKeys": {
55+
"tuple": {
56+
"items": [
57+
{
58+
"featureKey": "document"
59+
},
60+
{
61+
"featureKey": "summary"
62+
}
63+
]
64+
}
65+
},
66+
"version": "2.1.0"
67+
}
Lines changed: 15 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,15 @@
1+
{
2+
"featuresDict": {
3+
"features": {
4+
"document": {
5+
"pythonClassName": "tensorflow_datasets.core.features.text_feature.Text",
6+
"text": {}
7+
},
8+
"summary": {
9+
"pythonClassName": "tensorflow_datasets.core.features.text_feature.Text",
10+
"text": {}
11+
}
12+
}
13+
},
14+
"pythonClassName": "tensorflow_datasets.core.features.features_dict.FeaturesDict"
15+
}

tensorflow_datasets/testing/metadata/supported.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1290,7 +1290,7 @@ mt_opt/sd/1.0.0
12901290
mtnt/en-fr/1.0.0
12911291
mtnt/en-ja/1.0.0
12921292
mtnt/fr-en/1.0.0
1293-
multi_news/1.0.0
1293+
multi_news/2.1.0
12941294
multi_nli/1.1.0
12951295
multi_nli_mismatch/0.1.0
12961296
natural_instructions/1.0.1

0 commit comments

Comments
 (0)