Fix metadata JSON for ubuntu_dialogs_corpus dataset

datasets/ubuntu_dialogs_corpus/dataset_infos.json

@@ -1 +1 @@
-{"train": {"description": "Ubuntu Dialogue Corpus, a dataset containing almost 1 million multi-turn dialogues, with a total of over 7 million utterances and 100 million words. This provides a unique resource for research into building dialogue managers based on neural language models that can make use of large amounts of unlabeled data. The dataset has both the multi-turn property of conversations in the Dialog State Tracking Challenge datasets, and the unstructured nature of interactions from microblog services such as Twitter.\n", "citation": "@article{DBLP:journals/corr/LowePSP15,\n  author    = {Ryan Lowe and\n               Nissan Pow and\n               Iulian Serban and\n               Joelle Pineau},\n  title     = {The Ubuntu Dialogue Corpus: {A} Large Dataset for Research in Unstructured\n               Multi-Turn Dialogue Systems},\n  journal   = {CoRR},\n  volume    = {abs/1506.08909},\n  year      = {2015},\n  url       = {http://arxiv.org/abs/1506.08909},\n  archivePrefix = {arXiv},\n  eprint    = {1506.08909},\n  timestamp = {Mon, 13 Aug 2018 16:48:23 +0200},\n  biburl    = {https://dblp.org/rec/journals/corr/LowePSP15.bib},\n  bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n", "homepage": "https://github.com/rkadlec/ubuntu-ranking-dataset-creator", "license": "", "features": {"Context": {"dtype": "string", "id": null, "_type": "Value"}, "Utterance": {"dtype": "string", "id": null, "_type": "Value"}, "Label": {"dtype": "int32", "id": null, "_type": "Value"}}, "supervised_keys": null, "builder_name": "ubuntu_dialogs_corpus", "config_name": "train", "version": {"version_str": "2.0.0", "description": null, "datasets_version_to_prepare": null, "major": 2, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 65497027, "num_examples": 127422, "dataset_name": "ubuntu_dialogs_corpus"}}, "download_checksums": {}, "download_size": 0, "dataset_size": 65497027, "size_in_bytes": 65497027}}
+{"train": {"description": "Ubuntu Dialogue Corpus, a dataset containing almost 1 million multi-turn dialogues, with a total of over 7 million utterances and 100 million words. This provides a unique resource for research into building dialogue managers based on neural language models that can make use of large amounts of unlabeled data. The dataset has both the multi-turn property of conversations in the Dialog State Tracking Challenge datasets, and the unstructured nature of interactions from microblog services such as Twitter.\n", "citation": "@article{DBLP:journals/corr/LowePSP15,\n  author    = {Ryan Lowe and\n               Nissan Pow and\n               Iulian Serban and\n               Joelle Pineau},\n  title     = {The Ubuntu Dialogue Corpus: {A} Large Dataset for Research in Unstructured\n               Multi-Turn Dialogue Systems},\n  journal   = {CoRR},\n  volume    = {abs/1506.08909},\n  year      = {2015},\n  url       = {http://arxiv.org/abs/1506.08909},\n  archivePrefix = {arXiv},\n  eprint    = {1506.08909},\n  timestamp = {Mon, 13 Aug 2018 16:48:23 +0200},\n  biburl    = {https://dblp.org/rec/journals/corr/LowePSP15.bib},\n  bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n", "homepage": "https://github.com/rkadlec/ubuntu-ranking-dataset-creator", "license": "", "features": {"Context": {"dtype": "string", "id": null, "_type": "Value"}, "Utterance": {"dtype": "string", "id": null, "_type": "Value"}, "Label": {"dtype": "int32", "id": null, "_type": "Value"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "ubuntu_dialogs_corpus", "config_name": "train", "version": {"version_str": "2.0.0", "description": null, "major": 2, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 525126729, "num_examples": 1000000, "dataset_name": "ubuntu_dialogs_corpus"}}, "download_checksums": {}, "download_size": 0, "post_processing_size": null, "dataset_size": 525126729, "size_in_bytes": 525126729}, "dev_test": {"description": "Ubuntu Dialogue Corpus, a dataset containing almost 1 million multi-turn dialogues, with a total of over 7 million utterances and 100 million words. This provides a unique resource for research into building dialogue managers based on neural language models that can make use of large amounts of unlabeled data. The dataset has both the multi-turn property of conversations in the Dialog State Tracking Challenge datasets, and the unstructured nature of interactions from microblog services such as Twitter.\n", "citation": "@article{DBLP:journals/corr/LowePSP15,\n  author    = {Ryan Lowe and\n               Nissan Pow and\n               Iulian Serban and\n               Joelle Pineau},\n  title     = {The Ubuntu Dialogue Corpus: {A} Large Dataset for Research in Unstructured\n               Multi-Turn Dialogue Systems},\n  journal   = {CoRR},\n  volume    = {abs/1506.08909},\n  year      = {2015},\n  url       = {http://arxiv.org/abs/1506.08909},\n  archivePrefix = {arXiv},\n  eprint    = {1506.08909},\n  timestamp = {Mon, 13 Aug 2018 16:48:23 +0200},\n  biburl    = {https://dblp.org/rec/journals/corr/LowePSP15.bib},\n  bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n", "homepage": "https://github.com/rkadlec/ubuntu-ranking-dataset-creator", "license": "", "features": {"Context": {"dtype": "string", "id": null, "_type": "Value"}, "Ground Truth Utterance": {"dtype": "string", "id": null, "_type": "Value"}, "Distractor_0": {"dtype": "string", "id": null, "_type": "Value"}, "Distractor_1": {"dtype": "string", "id": null, "_type": "Value"}, "Distractor_2": {"dtype": "string", "id": null, "_type": "Value"}, "Distractor_3": {"dtype": "string", "id": null, "_type": "Value"}, "Distractor_4": {"dtype": "string", "id": null, "_type": "Value"}, "Distractor_5": {"dtype": "string", "id": null, "_type": "Value"}, "Distractor_6": {"dtype": "string", "id": null, "_type": "Value"}, "Distractor_7": {"dtype": "string", "id": null, "_type": "Value"}, "Distractor_8": {"dtype": "string", "id": null, "_type": "Value"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "ubuntu_dialogs_corpus", "config_name": "dev_test", "version": {"version_str": "2.0.0", "description": null, "major": 2, "minor": 0, "patch": 0}, "splits": {"test": {"name": "test", "num_bytes": 27060502, "num_examples": 18920, "dataset_name": "ubuntu_dialogs_corpus"}, "validation": {"name": "validation", "num_bytes": 27663181, "num_examples": 19560, "dataset_name": "ubuntu_dialogs_corpus"}}, "download_checksums": {}, "download_size": 0, "post_processing_size": null, "dataset_size": 54723683, "size_in_bytes": 54723683}}