├── LICENSE ├── README.md ├── data ├── results │ └── duplicate ├── test │ └── ru_test_10k_toxic └── train │ ├── MAT_FINAL_with_unigram_inflections.txt │ ├── dataset_200.xls │ └── ru_toxic_dataset.csv ├── metrics ├── __init__.py ├── aggregation_metric.py ├── content_similarity.py ├── language_quality.py ├── ru_metric.py └── style_trasnfer_accuracy.py ├── models ├── condBERT │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-37.pyc │ │ ├── choosers.cpython-37.pyc │ │ └── condbert.cpython-37.pyc │ ├── choosers.py │ ├── condbert.py │ └── multiword │ │ ├── .ipynb_checkpoints │ │ ├── masked_token_predictor_bert-checkpoint.py │ │ ├── predict-checkpoint.py │ │ └── predict_utils-checkpoint.py │ │ ├── __pycache__ │ │ ├── masked_token_predictor_bert.cpython-37.pyc │ │ └── predict_utils.cpython-37.pyc │ │ ├── masked_token_predictor_bert.py │ │ ├── multiword-base.ipynb │ │ ├── predict.py │ │ └── predict_utils.py └── detoxGPT │ ├── __init__.py │ └── __pycache__ │ ├── __init__.cpython-37.pyc │ ├── generate_transformers.cpython-37.pyc │ └── utils.cpython-37.pyc ├── notebooks └── rudetoxifier_inference.ipynb ├── requirements.txt └── settings └── __init__.py /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/README.md -------------------------------------------------------------------------------- /data/results/duplicate: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/data/results/duplicate -------------------------------------------------------------------------------- /data/test/ru_test_10k_toxic: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/data/test/ru_test_10k_toxic -------------------------------------------------------------------------------- /data/train/MAT_FINAL_with_unigram_inflections.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/data/train/MAT_FINAL_with_unigram_inflections.txt -------------------------------------------------------------------------------- /data/train/dataset_200.xls: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/data/train/dataset_200.xls -------------------------------------------------------------------------------- /data/train/ru_toxic_dataset.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/data/train/ru_toxic_dataset.csv -------------------------------------------------------------------------------- /metrics/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /metrics/aggregation_metric.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/metrics/aggregation_metric.py -------------------------------------------------------------------------------- /metrics/content_similarity.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/metrics/content_similarity.py -------------------------------------------------------------------------------- /metrics/language_quality.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/metrics/language_quality.py -------------------------------------------------------------------------------- /metrics/ru_metric.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/metrics/ru_metric.py -------------------------------------------------------------------------------- /metrics/style_trasnfer_accuracy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/metrics/style_trasnfer_accuracy.py -------------------------------------------------------------------------------- /models/condBERT/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/models/condBERT/__init__.py -------------------------------------------------------------------------------- /models/condBERT/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/models/condBERT/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /models/condBERT/__pycache__/choosers.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/models/condBERT/__pycache__/choosers.cpython-37.pyc -------------------------------------------------------------------------------- /models/condBERT/__pycache__/condbert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/models/condBERT/__pycache__/condbert.cpython-37.pyc -------------------------------------------------------------------------------- /models/condBERT/choosers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/models/condBERT/choosers.py -------------------------------------------------------------------------------- /models/condBERT/condbert.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/models/condBERT/condbert.py -------------------------------------------------------------------------------- /models/condBERT/multiword/.ipynb_checkpoints/masked_token_predictor_bert-checkpoint.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/models/condBERT/multiword/.ipynb_checkpoints/masked_token_predictor_bert-checkpoint.py -------------------------------------------------------------------------------- /models/condBERT/multiword/.ipynb_checkpoints/predict-checkpoint.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/models/condBERT/multiword/.ipynb_checkpoints/predict-checkpoint.py -------------------------------------------------------------------------------- /models/condBERT/multiword/.ipynb_checkpoints/predict_utils-checkpoint.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/models/condBERT/multiword/.ipynb_checkpoints/predict_utils-checkpoint.py -------------------------------------------------------------------------------- /models/condBERT/multiword/__pycache__/masked_token_predictor_bert.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/models/condBERT/multiword/__pycache__/masked_token_predictor_bert.cpython-37.pyc -------------------------------------------------------------------------------- /models/condBERT/multiword/__pycache__/predict_utils.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/models/condBERT/multiword/__pycache__/predict_utils.cpython-37.pyc -------------------------------------------------------------------------------- /models/condBERT/multiword/masked_token_predictor_bert.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/models/condBERT/multiword/masked_token_predictor_bert.py -------------------------------------------------------------------------------- /models/condBERT/multiword/multiword-base.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/models/condBERT/multiword/multiword-base.ipynb -------------------------------------------------------------------------------- /models/condBERT/multiword/predict.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/models/condBERT/multiword/predict.py -------------------------------------------------------------------------------- /models/condBERT/multiword/predict_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/models/condBERT/multiword/predict_utils.py -------------------------------------------------------------------------------- /models/detoxGPT/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/models/detoxGPT/__init__.py -------------------------------------------------------------------------------- /models/detoxGPT/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/models/detoxGPT/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /models/detoxGPT/__pycache__/generate_transformers.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/models/detoxGPT/__pycache__/generate_transformers.cpython-37.pyc -------------------------------------------------------------------------------- /models/detoxGPT/__pycache__/utils.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/models/detoxGPT/__pycache__/utils.cpython-37.pyc -------------------------------------------------------------------------------- /notebooks/rudetoxifier_inference.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/notebooks/rudetoxifier_inference.ipynb -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/requirements.txt -------------------------------------------------------------------------------- /settings/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/s-nlp/rudetoxifier/HEAD/settings/__init__.py --------------------------------------------------------------------------------