def _info(self):
features = datasets.Features({
"input_text": {
"table":
datasets.Sequence({
"column_header": datasets.Value("string"),
"row_number": datasets.Value("int16"),
"content": datasets.Value("string"),
}),
"context":
datasets.Value("string"),
},
"target_text": datasets.Value("string"),
})
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
supervised_keys=("input_text", "target_text"),
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION,
)
def _info(self):
return datasets.DatasetInfo(
# This is the description that will appear on the datasets page.
description=_DESCRIPTION,
# datasets.features.FeatureConnectors
features=datasets.Features(
{
"abstract_id": datasets.Value("int32"),
"text": datasets.Value("string"),
"location": datasets.Sequence(datasets.Value("int32")),
"label": datasets.Sequence(datasets.Value("string")),
# These are the features of your dataset like images, labels ...
}
),
# If there's a common (input, target) tuple from the features,
# specify them here. They'll be used if as_supervised=True in
# builder.as_dataset.
supervised_keys=None,
# Homepage of the dataset for documentation
homepage="https://github.com/BruceWen120/medal",
citation=_CITATION,
)
def _info(self):
# TODO(wiki_split): Specifies the datasets.DatasetInfo object
return datasets.DatasetInfo(
# This is the description that will appear on the datasets page.
description=_DESCRIPTION,
# datasets.features.FeatureConnectors
features=datasets.Features(
{
"complex_sentence": datasets.Value("string"),
"simple_sentence_1": datasets.Value("string"),
"simple_sentence_2": datasets.Value("string"),
# These are the features of your dataset like images, labels ...
}
),
# If there's a common (input, target) tuple from the features,
# specify them here. They'll be used if as_supervised=True in
# builder.as_dataset.
supervised_keys=None,
# Homepage of the dataset for documentation
homepage="https://dataset-homepage/",
citation=_CITATION,
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features(
{
"ID": datasets.Value("string"),
"Text": datasets.Value("string"),
"Pronoun": datasets.Value("string"),
"Pronoun-offset": datasets.Value("int32"),
"A": datasets.Value("string"),
"A-offset": datasets.Value("int32"),
"A-coref": datasets.Value("bool"),
"B": datasets.Value("string"),
"B-offset": datasets.Value("int32"),
"B-coref": datasets.Value("bool"),
"URL": datasets.Value("string"),
}
),
supervised_keys=None,
homepage="https://github.com/google-research-datasets/gap-coreference",
citation=_CITATION,
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"marketplace":
datasets.Value("string"),
"customer_id":
datasets.Value("string"),
"review_id":
datasets.Value("string"),
"product_id":
datasets.Value("string"),
"product_parent":
datasets.Value("string"),
"product_title":
datasets.Value("string"),
"product_category":
datasets.Value("string"),
"star_rating":
datasets.Value("int32"),
"helpful_votes":
datasets.Value("int32"),
"total_votes":
datasets.Value("int32"),
"vine":
datasets.features.ClassLabel(names=["N", "Y"]),
"verified_purchase":
datasets.features.ClassLabel(names=["N", "Y"]),
"review_headline":
datasets.Value("string"),
"review_body":
datasets.Value("string"),
"review_date":
datasets.Value("string"),
}),
supervised_keys=None,
homepage="https://s3.amazonaws.com/amazon-reviews-pds/readme.html",
citation=_CITATION,
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"premise":
datasets.Value("string"),
"hypothesis":
datasets.Value("string"),
"label":
datasets.ClassLabel(names=["not-entailment", "entailment"]),
"topic":
datasets.ClassLabel(names=[
"india", "news", "international", "entertainment", "sport",
"science"
]),
}),
supervised_keys=None,
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION,
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"fold":
datasets.Value("int32"),
"subfold":
datasets.Value("string"),
"words":
datasets.Sequence(datasets.Value("string")),
"segments":
datasets.Sequence(datasets.Value("string")),
"pos_tags":
datasets.Sequence(datasets.Value("string")),
}),
# If there's a common (input, target) tuple from the features,
# specify them here. They'll be used if as_supervised=True in
# builder.as_dataset.
supervised_keys=None,
homepage="https://alt.qcri.org/resources/da_resources/",
citation=_CITATION,
)
def _info(self):
if self.config.name == "alignments": # This is the name of the configuration selected in BUILDER_CONFIGS above
features = datasets.Features(
{
"source_id": datasets.Value("string"),
"target_id_list": datasets.Sequence(datasets.Value("string")),
}
)
else: # This is an example to show how to have different features for "first_domain" and "second_domain"
features = datasets.Features(
{
"id": datasets.Value("string"),
"question": {
"stem": datasets.Value("string"),
"choices": datasets.Sequence(
{
"text": datasets.Value("string"),
"label": datasets.Value("string"),
"para": datasets.Value("string"),
}
),
},
"answerKey": datasets.Value("string"),
"info": {
"grade": datasets.Value("int32"),
"subject": datasets.Value("string"),
"language": datasets.Value("string"),
},
}
)
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features, # Here we define them above because they are different between the two configurations
supervised_keys=None,
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION,
)
def _info(self):
features = datasets.Features({
"Question-ID":
datasets.Value("string"),
"RawQuestion":
datasets.Value("string"),
"ProcessedQuestion":
datasets.Value("string"),
"Parses":
datasets.Sequence({
"Parse-Id":
datasets.Value("string"),
"PotentialTopicEntityMention":
datasets.Value("string"),
"TopicEntityName":
datasets.Value("string"),
"TopicEntityMid":
datasets.Value("string"),
"InferentialChain":
datasets.Value("string"),
"Answers":
datasets.Sequence({
"AnswersMid":
datasets.Value("string"),
"AnswersName":
datasets.Sequence(datasets.Value("string")),
}),
}),
})
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
supervised_keys=None,
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION,
)
def _info(self):
# TODO(blended_skill_talk): Specifies the datasets.DatasetInfo object
return datasets.DatasetInfo(
# This is the description that will appear on the datasets page.
description=_DESCRIPTION,
# datasets.features.FeatureConnectors
features=datasets.Features({
"personas":
datasets.features.Sequence(datasets.Value("string")),
"additional_context":
datasets.Value("string"),
"previous_utterance":
datasets.features.Sequence(datasets.Value("string")),
"context":
datasets.Value("string"),
"free_messages":
datasets.features.Sequence(datasets.Value("string")),
"guided_messages":
datasets.features.Sequence(datasets.Value("string")),
"suggestions":
datasets.features.Sequence(
{task: datasets.Value("string")
for task in _TASK}),
"guided_chosen_suggestions":
datasets.features.Sequence(datasets.Value("string")),
"label_candidates":
datasets.features.Sequence(
datasets.features.Sequence(datasets.Value("string"))),
# These are the features of your dataset like images, labels ...
}),
# If there's a common (input, target) tuple from the features,
# specify them here. They'll be used if as_supervised=True in
# builder.as_dataset.
supervised_keys=None,
# Homepage of the dataset for documentation
homepage="https://parl.ai/projects/bst/",
citation=_CITATION,
)
def _info(self):
# This method specifies the datasets.DatasetInfo object which contains informations and typings for the dataset
if self.config.name == "first_domain": # This is the name of the configuration selected in BUILDER_CONFIGS above
features = datasets.Features(
{
"sequence": datasets.Value("string"),
"ECnumber": datasets.features.ClassLabel(names=["1", "2", "3", "4", "5", "6", "7"])
# TODO: specify the main classes of anzymes by name?
# These are the features of your dataset like images, labels ...
}
)
elif self.config.name == "second_domain": # This is an example to show how to have different features for "first_domain" and "second_domain"
features = datasets.Features(
{
"sequence": datasets.Value("string"),
"ECnumber_one": datasets.Value("string"),
"ECnumber_two": datasets.Value("string")
# These are the features of your dataset like images, labels ...
}
)
return datasets.DatasetInfo(
# This is the description that will appear on the datasets page.
description=_DESCRIPTION,
# This defines the different columns of the dataset and their types
features=features, # Here we define them above because they are different between the two configurations
# If there's a common (input, target) tuple from the features,
# specify them here. They'll be used if as_supervised=True in
# builder.as_dataset.
supervised_keys=None,
# Homepage of the dataset for documentation
homepage=_HOMEPAGE,
# License for the dataset if available
license=_LICENSE,
# Citation for the dataset
citation=_CITATION,
task_templates=[TextClassification(text_column="text", label_column="label")],
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"text":
datasets.Value("string"),
"text_type":
datasets.Value("string"),
"topics":
datasets.Sequence(datasets.Value("string")),
"lewis_split":
datasets.Value("string"),
"cgis_split":
datasets.Value("string"),
"old_id":
datasets.Value("string"),
"new_id":
datasets.Value("string"),
"places":
datasets.Sequence(datasets.Value("string")),
"people":
datasets.Sequence(datasets.Value("string")),
"orgs":
datasets.Sequence(datasets.Value("string")),
"exchanges":
datasets.Sequence(datasets.Value("string")),
"date":
datasets.Value("string"),
"title":
datasets.Value("string"),
}),
# No default supervised_keys (as we have to pass both premise
# and hypothesis as input).
supervised_keys=None,
homepage=
"https://kdd.ics.uci.edu/databases/reuters21578/reuters21578.html",
citation=_CITATION,
)
def _info(self):
return datasets.DatasetInfo(
# This is the description that will appear on the datasets page.
description=_DESCRIPTION,
# datasets.features.FeatureConnectors
features=datasets.Features({
"topic_id":
datasets.Value("string"),
"topic_name":
datasets.Value("string"),
"test_id":
datasets.Value("string"),
"document_id":
datasets.Value("string"),
"document_str":
datasets.Value("string"),
"question_id":
datasets.Value("string"),
"question_str":
datasets.Value("string"),
"answer_options":
datasets.features.Sequence({
"answer_id":
datasets.Value("string"),
"answer_str":
datasets.Value("string")
}),
"correct_answer_id":
datasets.Value("string"),
"correct_answer_str":
datasets.Value("string"),
}),
# No default supervised keys because both passage and question are used
# to determine the correct answer.
supervised_keys=None,
homepage="http://nlp.uned.es/clef-qa/repository/pastCampaigns.php",
citation=_CITATION,
)
def _info(self):
features = datasets.Features({
"client_id":
datasets.Value("string"),
"path":
datasets.Value("string"),
"audio":
datasets.Audio(sampling_rate=48_000),
"sentence":
datasets.Value("string"),
"up_votes":
datasets.Value("int64"),
"down_votes":
datasets.Value("int64"),
"age":
datasets.Value("string"),
"gender":
datasets.Value("string"),
"accent":
datasets.Value("string"),
"locale":
datasets.Value("string"),
"segment":
datasets.Value("string"),
})
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
supervised_keys=None,
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION,
task_templates=[
AutomaticSpeechRecognition(audio_file_path_column="path",
transcription_column="sentence")
],
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"promptID":
datasets.Value("int32"),
"pairID":
datasets.Value("string"),
"premise":
datasets.Value("string"),
"premise_binary_parse":
datasets.Value(
"string"), # parses in unlabeled binary-branching format
"premise_parse":
datasets.Value(
"string"
), # sentence as parsed by the Stanford PCFG Parser 3.5.2
"hypothesis":
datasets.Value("string"),
"hypothesis_binary_parse":
datasets.Value(
"string"), # parses in unlabeled binary-branching format
"hypothesis_parse":
datasets.Value(
"string"
), # sentence as parsed by the Stanford PCFG Parser 3.5.2
"genre":
datasets.Value("string"),
"label":
datasets.features.ClassLabel(
names=["entailment", "neutral", "contradiction"]),
}),
# No default supervised_keys (as we have to pass both premise
# and hypothesis as input).
supervised_keys=None,
homepage="https://www.nyu.edu/projects/bowman/multinli/",
citation=_CITATION,
)
def _info(self):
# TODO(com_qa): Specifies the datasets.DatasetInfo object
return datasets.DatasetInfo(
# This is the description that will appear on the datasets page.
description=_DESCRIPTION,
# datasets.features.FeatureConnectors
features=datasets.Features({
"cluster_id":
datasets.Value("string"),
"questions":
datasets.features.Sequence(datasets.Value("string")),
"answers":
datasets.features.Sequence(datasets.Value("string")),
# These are the features of your dataset like images, labels ...
}),
# If there's a common (input, target) tuple from the features,
# specify them here. They'll be used if as_supervised=True in
# builder.as_dataset.
supervised_keys=None,
# Homepage of the dataset for documentation
homepage="http://qa.mpi-inf.mpg.de/comqa/",
citation=_CITATION,
)
def _info(self):
features = datasets.Features(
{
"category_name": datasets.Value("string"),
"question_query": datasets.Value("string"),
"keyword_query": datasets.Value("string"),
"answers": datasets.features.Sequence(
{
"id": datasets.Value("string"),
"title": datasets.Value("string"),
"exact_answer": datasets.Value("string"),
}
),
}
)
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
supervised_keys=None,
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION,
)
def _info(self):
features = datasets.Features({
"lemma":
datasets.Value("string"),
"forms":
datasets.Sequence(
dict([("word", datasets.Value("string"))] +
[(cat,
datasets.Sequence(datasets.ClassLabel(names=tasks)))
for cat, tasks in _CATEGORIES.items()] +
[("Other", datasets.Sequence(datasets.Value("string"))
)] # for misspecified tags
)),
})
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=
features, # Here we define them above because they are different between the two configurations
supervised_keys=None,
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION,
)
def _info(self):
features = datasets.Features({
"id":
datasets.Value("string"),
"source":
datasets.Value("string"),
"alignment_type":
datasets.Value("string"),
"alignment_quality":
datasets.Value("string"),
"translation":
datasets.features.Translation(languages=["en", "hi"]),
})
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
supervised_keys=None,
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION,
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features(
{
"text": datasets.Value("string"),
"label": datasets.features.ClassLabel(
names=[
"Web",
"Panorama",
"International",
"Wirtschaft",
"Sport",
"Inland",
"Etat",
"Wissenschaft",
"Kultur",
]
),
}
),
homepage="https://tblock.github.io/10kGNAD/",
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"count":
datasets.Value("int64"),
"hate_speech_count":
datasets.Value("int64"),
"offensive_language_count":
datasets.Value("int64"),
"neither_count":
datasets.Value("int64"),
"class":
datasets.ClassLabel(
names=["hate speech", "offensive language", "neither"]),
"tweet":
datasets.Value("string"),
}),
supervised_keys=("tweet", "class"),
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION,
)
def _info(self):
features = datasets.Features({
"review_body":
datasets.Value("string"),
"review_summary":
datasets.Value("string"),
"star_rating":
datasets.ClassLabel(names=[str(i) for i in range(1, 6)]),
})
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
supervised_keys=None,
homepage="http://www.lsi.us.es/~fermin/index.php/Datasets",
license=_LICENSE,
citation=_CITATION,
task_templates=[
TextClassification(text_column="review_body",
label_column="star_rating"),
TextClassification(text_column="review_summary",
label_column="star_rating"),
],
)
def _info(self):
features = datasets.Features({
"total_annotation_count":
datasets.Value("int32"),
"hate_speech_annotations":
datasets.Value("int32"),
"offensive_language_annotations":
datasets.Value("int32"),
"neither_annotations":
datasets.Value("int32"),
"label":
datasets.ClassLabel(
names=["hate-speech", "offensive-language", "neither"]),
"tweet":
datasets.Value("string"),
})
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
supervised_keys=("tweet", "label"),
homepage=_HOMEPAGE,
citation=_CITATION,
)
def _info(self):
if self.config.name.startswith("tlc"):
features = datasets.Features(
{
"ch_num": datasets.Value("string"),
"title": datasets.Value("string"),
"text": datasets.Sequence(datasets.Sequence(datasets.Value("string"))),
}
)
else:
features = datasets.Features(
{
"text": datasets.Sequence((datasets.Value("string"))),
}
)
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
supervised_keys=None,
homepage=_HOMEPAGE,
citation=_CITATION,
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features(
{
"id": datasets.Value("string"),
"annotator": datasets.Value("int32"),
"position": datasets.Value("int32"),
"question": datasets.Value("string"),
"table_file": datasets.Value("string"),
"table_header": datasets.features.Sequence(datasets.Value("string")),
"table_data": datasets.features.Sequence(datasets.features.Sequence(datasets.Value("string"))),
"answer_coordinates": datasets.features.Sequence(
{"row_index": datasets.Value("int32"), "column_index": datasets.Value("int32")}
),
"answer_text": datasets.features.Sequence(datasets.Value("string")),
}
),
supervised_keys=None,
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION,
)
def _info(self):
return ds.DatasetInfo(
description="",
citation="",
homepage="",
license="",
features=ds.Features(
{
"id": ds.Value("string"),
"title": ds.Value("string"),
"context": ds.Value("string"),
"question": ds.Value("string"),
"answers": ds.features.Sequence(
{"text": ds.Value("string"), "answer_start": ds.Value("int32")}
),
}
),
task_templates=[
QuestionAnsweringExtractive(
question_column="question", context_column="context", answers_column="answers"
)
],
)
def _info(self):
features = datasets.Features({
"question": datasets.Value("string"),
"answer": datasets.Value("string"),
# These are the features of your dataset like images, labels ...
})
return datasets.DatasetInfo(
# This is the description that will appear on the datasets page.
description=_DESCRIPTION,
# This defines the different columns of the dataset and their types
features=
features, # Here we define them above because they are different between the two configurations
# If there's a common (input, target) tuple from the features,
# specify them here. They'll be used if as_supervised=True in
# builder.as_dataset.
supervised_keys=None,
# Homepage of the dataset for documentation
homepage=_HOMEPAGE,
# License for the dataset if available
license=_LICENSE,
# Citation for the dataset
citation=_CITATION,
)
def _info(self):
features = datasets.Features({
"id":
datasets.Value("string"),
"url":
datasets.Value("string"),
"qid":
datasets.Value("int32"),
"question":
datasets.Value("string"),
"answers":
datasets.Sequence(datasets.Value("string")),
"correct":
datasets.Value("string"),
})
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
supervised_keys=None,
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION,
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"id":
datasets.Value("string"),
"tokens":
datasets.Sequence(datasets.Value("string")),
"bboxes":
datasets.Sequence(datasets.Sequence(datasets.Value("int64"))),
"ner_tags":
datasets.Sequence(
datasets.features.ClassLabel(names=[
"O", "B-HEADER", "I-HEADER", "B-QUESTION",
"I-QUESTION", "B-ANSWER", "I-ANSWER"
])),
"image":
datasets.Array3D(shape=(3, 224, 224), dtype="uint8"),
}),
supervised_keys=None,
homepage="https://guillaumejaume.github.io/FUNSD/",
citation=_CITATION,
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"id":
datasets.Value("string"),
"audio":
datasets.features.Audio(sampling_rate=22050),
"file":
datasets.Value("string"),
"text":
datasets.Value("string"),
"normalized_text":
datasets.Value("string"),
}),
supervised_keys=("file", "text"),
homepage=_URL,
citation=_CITATION,
task_templates=[
AutomaticSpeechRecognition(audio_file_path_column="file",
transcription_column="text")
],
)
