Skip to content

euroeval.dataset_configs.latvian

[docs] module euroeval.dataset_configs.latvian 

 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
82
83
84
85
86
87
88
89
90
91
92
93
94
95
"""All Latvian dataset configurations used in EuroEval."""

from ..data_models import DatasetConfig
from ..enums import ModelType
from ..languages import LV
from ..tasks import COMMON_SENSE, KNOW, LA, NER, RC, SENT, SUMM

### Official datasets ###

LATVIAN_TWITTER_SENTIMENT_CONFIG = DatasetConfig(
    name="latvian-twitter-sentiment",
    pretty_name="the truncated version of the Latvian sentiment classification dataset",
    huggingface_id="EuroEval/latvian-twitter-sentiment-mini",
    task=SENT,
    languages=[LV],
)

SCALA_LV_CONFIG = DatasetConfig(
    name="scala-lv",
    pretty_name="the Latvian part of the linguistic acceptability dataset ScaLA",
    huggingface_id="EuroEval/scala-lv",
    task=LA,
    languages=[LV],
)

FULLSTACK_NER_LV_CONFIG = DatasetConfig(
    name="fullstack-ner-lv",
    pretty_name="the truncated version of the FullStack NER dataset",
    huggingface_id="EuroEval/fullstack-ner-lv-mini",
    task=NER,
    languages=[LV],
)

MULTI_WIKI_QA_LV_CONFIG = DatasetConfig(
    name="multi-wiki-qa-lv",
    pretty_name="the truncated version of the Latvian part of the reading "
    "comprehension dataset MultiWikiQA",
    huggingface_id="EuroEval/multi-wiki-qa-lv-mini",
    task=RC,
    languages=[LV],
)

LSM_CONFIG = DatasetConfig(
    name="lsm",
    pretty_name="the truncated version of the Latvian summarisation dataset LSM",
    huggingface_id="EuroEval/lsm-mini",
    task=SUMM,
    languages=[LV],
)


MMLU_LV_CONFIG = DatasetConfig(
    name="mmlu-lv",
    pretty_name="the truncated version of the Latvian knowledge dataset MMLU-lv, "
    "translated from the English MMLU dataset",
    huggingface_id="EuroEval/mmlu-lv-mini",
    task=KNOW,
    languages=[LV],
)

COPA_LV_CONFIG = DatasetConfig(
    name="copa-lv",
    pretty_name="the Latvian common-sense reasoning dataset COPA-lv, translated from "
    "the English COPA dataset",
    huggingface_id="EuroEval/copa-lv",
    task=COMMON_SENSE,
    languages=[LV],
    _labels=["a", "b"],
)


### Unofficial datasets ###

WIKIANN_LV_CONFIG = DatasetConfig(
    name="wikiann-lv",
    pretty_name="the truncated version of the Latvian part of the named entity "
    "recognition dataset WikiANN",
    huggingface_id="EuroEval/wikiann-lv-mini",
    task=NER,
    languages=[LV],
    unofficial=True,
)

WINOGRANDE_LV_CONFIG = DatasetConfig(
    name="winogrande-lv",
    pretty_name="the Latvian common-sense reasoning dataset Winogrande-lv, translated "
    "from the English Winogrande dataset",
    huggingface_id="EuroEval/winogrande-lv",
    task=COMMON_SENSE,
    languages=[LV],
    splits=["train", "test"],
    _labels=["a", "b"],
    _allowed_model_types=[ModelType.GENERATIVE],
    unofficial=True,
)