Skip to content

euroeval.dataset_configs.italian

docs module euroeval.dataset_configs.italian 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
"""All Italian dataset configurations used in EuroEval."""

from ..data_models import DatasetConfig
from ..languages import IT
from ..tasks import COMMON_SENSE, KNOW, LA, NER, RC, SENT, SUMM

### Official datasets ###

SENTIPOLC_CONFIG = DatasetConfig(
    name="sentipolc16",
    pretty_name="the truncated version of the Italian sentiment classification "
    "dataset Sentipolc-16",
    huggingface_id="EuroEval/sentipolc16-mini",
    task=SENT,
    languages=[IT],
)

SCALA_IT_CONFIG = DatasetConfig(
    name="scala-it",
    pretty_name="the Italian part of the linguistic acceptability dataset ScaLA",
    huggingface_id="EuroEval/scala-it",
    task=LA,
    languages=[IT],
)

MULTINERD_IT_CONFIG = DatasetConfig(
    name="multinerd-it",
    pretty_name="the truncated version of the Italian part of the named "
    "entity recognition dataset MultiNERD",
    huggingface_id="EuroEval/multinerd-mini-it",
    task=NER,
    languages=[IT],
)

SQUAD_IT_CONFIG = DatasetConfig(
    name="squad-it",
    pretty_name="the truncated version of the Italian reading comprehension dataset "
    "SQuAD-it, translated from the English SQuAD dataset",
    huggingface_id="EuroEval/squad-it-mini",
    task=RC,
    languages=[IT],
)

ILPOST_SUM_CONFIG = DatasetConfig(
    name="ilpost-sum",
    pretty_name="the truncated version of the Italian summarisation dataset IlPost-Sum",
    huggingface_id="EuroEval/ilpost-sum",
    task=SUMM,
    languages=[IT],
)

MMLU_IT_CONFIG = DatasetConfig(
    name="mmlu-it",
    pretty_name="the truncated version of the Italian knowledge dataset MMLU-it, "
    "translated from the English MMLU dataset",
    huggingface_id="EuroEval/mmlu-it-mini",
    task=KNOW,
    languages=[IT],
)

HELLASWAG_IT_CONFIG = DatasetConfig(
    name="hellaswag-it",
    pretty_name="the truncated version of the Italian common-sense reasoning dataset "
    "HellaSwag-it, translated from the English HellaSwag dataset",
    huggingface_id="EuroEval/hellaswag-it-mini",
    task=COMMON_SENSE,
    languages=[IT],
)


### Unofficial datasets ###

WIKINEURAL_IT_CONFIG = DatasetConfig(
    name="wikineural-it",
    pretty_name="the truncated version of the Italian named "
    "entity recognition dataset WikiNEuRal IT",
    huggingface_id="EuroEval/wikineural-mini-it",
    task=NER,
    languages=[IT],
    unofficial=True,
)