CC BY 4.0 synthetic dataset
Bilingual Production Vocabulary
Role and workflow terminology pairs.
Validation summary
{
"records": 24,
"train": 18,
"evaluation": 6,
"synthetic_only": true,
"leaked_groups": 0
}Sample records
[
{
"record_id": "bilingual-production-vocabulary-01-1",
"group_id": "bilingual-production-vocabulary-group-01",
"split": "evaluation",
"label_en": "brief positive example",
"label_ru": "brief: корректный пример",
"synthetic": true,
"payload": {
"term_en": "brief",
"term_ru": "термин-1",
"context": "production"
}
},
{
"record_id": "bilingual-production-vocabulary-01-2",
"group_id": "bilingual-production-vocabulary-group-01",
"split": "evaluation",
"label_en": "brief negative example",
"label_ru": "brief: ошибочный пример",
"synthetic": true,
"payload": {
"term_en": "brief",
"term_ru": "термин-1",
"context": "ambiguous"
}
},
{
"record_id": "bilingual-production-vocabulary-02-1",
"group_id": "bilingual-production-vocabulary-group-02",
"split": "train",
"label_en": "treatment positive example",
"label_ru": "treatment: корректный пример",
"synthetic": true,
"payload": {
"term_en": "treatment",
"term_ru": "термин-2",
"context": "production"
}
},
{
"record_id": "bilingual-production-vocabulary-02-2",
"group_id": "bilingual-production-vocabulary-group-02",
"split": "train",
"label_en": "treatment negative example",
"label_ru": "treatment: ошибочный пример",
"synthetic": true,
"payload": {
"term_en": "treatment",
"term_ru": "термин-2",
"context": "ambiguous"
}
}
]