#381 fix

arekit/contrib/utils/bert/samplers.py

@@ -0,0 +1,18 @@
+from arekit.common.data.input.providers.label.multiple import MultipleLabelProvider
+from arekit.common.data.input.providers.rows.samples import BaseSampleRowProvider
+from arekit.common.data.input.providers.text.single import BaseSingleTextProvider
+from arekit.common.data.input.terms_mapper import OpinionContainingTextTermsMapper
+from arekit.contrib.bert.input.providers.text_pair import PairTextProvider
+
+
+def create_sample_provider(label_scaler, text_b_template, text_terms_mapper, text_b_labels_fmt=None):
+    assert(isinstance(text_terms_mapper, OpinionContainingTextTermsMapper))
+
+    text_provider = BaseSingleTextProvider(text_terms_mapper=text_terms_mapper) \
+        if text_b_labels_fmt is None else PairTextProvider(text_b_template=text_b_template,
+                                                           text_b_labels_fmt=text_b_labels_fmt,
+                                                           text_terms_mapper=text_terms_mapper)
+
+    label_provider = MultipleLabelProvider(label_scaler=label_scaler)
+
+    return BaseSampleRowProvider(text_provider=text_provider, label_provider=label_provider)

arekit/contrib/utils/bert/text_b_rus.py

@@ -0,0 +1,18 @@
+from enum import Enum
+
+
+class BertTextBTemplates(Enum):
+    """
+    Default, based on COLA, but includes an extra text_b.
+        text_b: Pseudo-sentence w/o S.P (S.P -- sentiment polarity)
+        text_b: Question w/o S.P (S.P -- sentiment polarity)
+
+    Multilabel variant
+
+    Notation were taken from paper:
+    https://www.aclweb.org/anthology/N19-1035.pdf
+    """
+
+    NLI = '{subject} к {object} в контексте : << {context} >>'
+
+    QA = 'Что вы думаете по поводу отношения {subject} к {object} в контексте : << {context} >> ?'