Skip to content

update discofuse link cc @ekQ #2541

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
lhoestq merged 2 commits into from
Jun 28, 2021
Merged

update discofuse link cc @ekQ #2541

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b096553
update discofuse link cc @ekQ
VictorSanh Jun 23, 2021
ccff90c
update urls checksums
lhoestq Jun 28, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion datasets/discofuse/dataset_infos.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
{"discofuse-sport": {"description": " DISCOFUSE is a large scale dataset for discourse-based sentence fusion.\n", "citation": "@InProceedings{GevaEtAl2019,\n title = {DiscoFuse: A Large-Scale Dataset for Discourse-Based Sentence Fusion},\n author = {Geva, Mor and Malmi, Eric and Szpektor, Idan and Berant, Jonathan},\n booktitle = {Proceedings of the 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics},\n note = {arXiv preprint arXiv:1902.10526},\n year = {2019}\n}\n\n", "homepage": "https://github.com/google-research-datasets/discofuse", "license": "", "features": {"connective_string": {"dtype": "string", "id": null, "_type": "Value"}, "discourse_type": {"dtype": "string", "id": null, "_type": "Value"}, "coherent_second_sentence": {"dtype": "string", "id": null, "_type": "Value"}, "has_coref_type_pronoun": {"dtype": "float32", "id": null, "_type": "Value"}, "incoherent_first_sentence": {"dtype": "string", "id": null, "_type": "Value"}, "incoherent_second_sentence": {"dtype": "string", "id": null, "_type": "Value"}, "has_coref_type_nominal": {"dtype": "float32", "id": null, "_type": "Value"}, "coherent_first_sentence": {"dtype": "string", "id": null, "_type": "Value"}}, "post_processed": null, "supervised_keys": null, "builder_name": "discofuse", "config_name": "discofuse-sport", "version": {"version_str": "1.0.0", "description": "", "major": 1, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 14736279993, "num_examples": 43291020, "dataset_name": "discofuse"}, "test": {"name": "test", "num_bytes": 151656323, "num_examples": 445521, "dataset_name": "discofuse"}, "validation": {"name": "validation", "num_bytes": 150207737, "num_examples": 440902, "dataset_name": "discofuse"}}, "download_checksums": {"https://storage.googleapis.com/discofuse.appspot.com/discofuse_v1_sports.zip": {"num_bytes": 4326637746, "checksum": "a390083c7923e11efeeea04a9a79074149e5ef9be614466f50aec28f1a5eec41"}}, "download_size": 4326637746, "post_processing_size": null, "dataset_size": 15038144053, "size_in_bytes": 19364781799}, "discofuse-wikipedia": {"description": " DISCOFUSE is a large scale dataset for discourse-based sentence fusion.\n", "citation": "@InProceedings{GevaEtAl2019,\n title = {DiscoFuse: A Large-Scale Dataset for Discourse-Based Sentence Fusion},\n author = {Geva, Mor and Malmi, Eric and Szpektor, Idan and Berant, Jonathan},\n booktitle = {Proceedings of the 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics},\n note = {arXiv preprint arXiv:1902.10526},\n year = {2019}\n}\n\n", "homepage": "https://github.com/google-research-datasets/discofuse", "license": "", "features": {"connective_string": {"dtype": "string", "id": null, "_type": "Value"}, "discourse_type": {"dtype": "string", "id": null, "_type": "Value"}, "coherent_second_sentence": {"dtype": "string", "id": null, "_type": "Value"}, "has_coref_type_pronoun": {"dtype": "float32", "id": null, "_type": "Value"}, "incoherent_first_sentence": {"dtype": "string", "id": null, "_type": "Value"}, "incoherent_second_sentence": {"dtype": "string", "id": null, "_type": "Value"}, "has_coref_type_nominal": {"dtype": "float32", "id": null, "_type": "Value"}, "coherent_first_sentence": {"dtype": "string", "id": null, "_type": "Value"}}, "post_processed": null, "supervised_keys": null, "builder_name": "discofuse", "config_name": "discofuse-wikipedia", "version": {"version_str": "1.0.0", "description": "", "major": 1, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 6377924196, "num_examples": 16310585, "dataset_name": "discofuse"}, "test": {"name": "test", "num_bytes": 64008158, "num_examples": 163657, "dataset_name": "discofuse"}, "validation": {"name": "validation", "num_bytes": 65682035, "num_examples": 168081, "dataset_name": "discofuse"}}, "download_checksums": {"https://storage.googleapis.com/discofuse.appspot.com/discofuse_v1_wikipedia.zip": {"num_bytes": 1717422334, "checksum": "e8a5ec52cdd9820ce9b410b47c3a57a49a300470c976202cd7caab613658ebfe"}}, "download_size": 1717422334, "post_processing_size": null, "dataset_size": 6507614389, "size_in_bytes": 8225036723}}
{"discofuse-sport": {"description": " DISCOFUSE is a large scale dataset for discourse-based sentence fusion.\n", "citation": "@InProceedings{GevaEtAl2019,\n title = {DiscoFuse: A Large-Scale Dataset for Discourse-Based Sentence Fusion},\n author = {Geva, Mor and Malmi, Eric and Szpektor, Idan and Berant, Jonathan},\n booktitle = {Proceedings of the 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics},\n note = {arXiv preprint arXiv:1902.10526},\n year = {2019}\n}\n\n", "homepage": "https://github.com/google-research-datasets/discofuse", "license": "", "features": {"connective_string": {"dtype": "string", "id": null, "_type": "Value"}, "discourse_type": {"dtype": "string", "id": null, "_type": "Value"}, "coherent_second_sentence": {"dtype": "string", "id": null, "_type": "Value"}, "has_coref_type_pronoun": {"dtype": "float32", "id": null, "_type": "Value"}, "incoherent_first_sentence": {"dtype": "string", "id": null, "_type": "Value"}, "incoherent_second_sentence": {"dtype": "string", "id": null, "_type": "Value"}, "has_coref_type_nominal": {"dtype": "float32", "id": null, "_type": "Value"}, "coherent_first_sentence": {"dtype": "string", "id": null, "_type": "Value"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "discofuse", "config_name": "discofuse-sport", "version": {"version_str": "1.0.0", "description": "", "major": 1, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 14736279993, "num_examples": 43291020, "dataset_name": "discofuse"}, "test": {"name": "test", "num_bytes": 151656323, "num_examples": 445521, "dataset_name": "discofuse"}, "validation": {"name": "validation", "num_bytes": 150207737, "num_examples": 440902, "dataset_name": "discofuse"}}, "download_checksums": {"https://storage.googleapis.com/gresearch/discofuse/discofuse_v1_sports.zip": {"num_bytes": 4326637746, "checksum": "a390083c7923e11efeeea04a9a79074149e5ef9be614466f50aec28f1a5eec41"}}, "download_size": 4326637746, "post_processing_size": null, "dataset_size": 15038144053, "size_in_bytes": 19364781799}, "discofuse-wikipedia": {"description": " DISCOFUSE is a large scale dataset for discourse-based sentence fusion.\n", "citation": "@InProceedings{GevaEtAl2019,\n title = {DiscoFuse: A Large-Scale Dataset for Discourse-Based Sentence Fusion},\n author = {Geva, Mor and Malmi, Eric and Szpektor, Idan and Berant, Jonathan},\n booktitle = {Proceedings of the 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics},\n note = {arXiv preprint arXiv:1902.10526},\n year = {2019}\n}\n\n", "homepage": "https://github.com/google-research-datasets/discofuse", "license": "", "features": {"connective_string": {"dtype": "string", "id": null, "_type": "Value"}, "discourse_type": {"dtype": "string", "id": null, "_type": "Value"}, "coherent_second_sentence": {"dtype": "string", "id": null, "_type": "Value"}, "has_coref_type_pronoun": {"dtype": "float32", "id": null, "_type": "Value"}, "incoherent_first_sentence": {"dtype": "string", "id": null, "_type": "Value"}, "incoherent_second_sentence": {"dtype": "string", "id": null, "_type": "Value"}, "has_coref_type_nominal": {"dtype": "float32", "id": null, "_type": "Value"}, "coherent_first_sentence": {"dtype": "string", "id": null, "_type": "Value"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "discofuse", "config_name": "discofuse-wikipedia", "version": {"version_str": "1.0.0", "description": "", "major": 1, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 6377924196, "num_examples": 16310585, "dataset_name": "discofuse"}, "test": {"name": "test", "num_bytes": 64008158, "num_examples": 163657, "dataset_name": "discofuse"}, "validation": {"name": "validation", "num_bytes": 65682035, "num_examples": 168081, "dataset_name": "discofuse"}}, "download_checksums": {"https://storage.googleapis.com/gresearch/discofuse/discofuse_v1_wikipedia.zip": {"num_bytes": 1717422334, "checksum": "e8a5ec52cdd9820ce9b410b47c3a57a49a300470c976202cd7caab613658ebfe"}}, "download_size": 1717422334, "post_processing_size": null, "dataset_size": 6507614389, "size_in_bytes": 8225036723}}
2 changes: 1 addition & 1 deletion datasets/discofuse/discofuse.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
import datasets


_URL_ = "https://storage.googleapis.com/discofuse.appspot.com/"
_URL_ = "https://storage.googleapis.com/gresearch/discofuse/"
_CITATION = """\
@InProceedings{GevaEtAl2019,
title = {DiscoFuse: A Large-Scale Dataset for Discourse-Based Sentence Fusion},
Expand Down