├── .gitignore ├── LICENSE ├── README.md ├── __images__ └── seq-to-seq-DNC.jpg ├── environment.yml ├── notebooks ├── .gitkeep ├── Data Preparation.ipynb ├── Preprocessing.ipynb └── Text Normalization Demo.ipynb ├── results ├── .gitkeep ├── base-paper_classwise_accuracy.csv ├── english │ ├── Semiotic_Class-wise_Accuracy.png │ ├── classwise_accuracy.csv │ ├── mistakes.csv │ └── normalized.csv └── russian │ ├── .gitkeep │ ├── Semiotic_Class-wise_Accuracy.png │ ├── classwise_accuracy.csv │ ├── mistakes.csv │ └── normalized.csv ├── setup.sh └── src ├── .gitkeep ├── DNCnormalize.py ├── Encoder.py ├── XGBclassify.py ├── classification_report.py ├── lib ├── access.py ├── addressing.py ├── dnc.py ├── seq2seq.py └── util.py ├── preprocessing.py └── utils.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/README.md -------------------------------------------------------------------------------- /__images__/seq-to-seq-DNC.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/__images__/seq-to-seq-DNC.jpg -------------------------------------------------------------------------------- /environment.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/environment.yml -------------------------------------------------------------------------------- /notebooks/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /notebooks/Data Preparation.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/notebooks/Data Preparation.ipynb -------------------------------------------------------------------------------- /notebooks/Preprocessing.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/notebooks/Preprocessing.ipynb -------------------------------------------------------------------------------- /notebooks/Text Normalization Demo.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/notebooks/Text Normalization Demo.ipynb -------------------------------------------------------------------------------- /results/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /results/base-paper_classwise_accuracy.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/results/base-paper_classwise_accuracy.csv -------------------------------------------------------------------------------- /results/english/Semiotic_Class-wise_Accuracy.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/results/english/Semiotic_Class-wise_Accuracy.png -------------------------------------------------------------------------------- /results/english/classwise_accuracy.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/results/english/classwise_accuracy.csv -------------------------------------------------------------------------------- /results/english/mistakes.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/results/english/mistakes.csv -------------------------------------------------------------------------------- /results/english/normalized.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/results/english/normalized.csv -------------------------------------------------------------------------------- /results/russian/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /results/russian/Semiotic_Class-wise_Accuracy.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/results/russian/Semiotic_Class-wise_Accuracy.png -------------------------------------------------------------------------------- /results/russian/classwise_accuracy.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/results/russian/classwise_accuracy.csv -------------------------------------------------------------------------------- /results/russian/mistakes.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/results/russian/mistakes.csv -------------------------------------------------------------------------------- /results/russian/normalized.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/results/russian/normalized.csv -------------------------------------------------------------------------------- /setup.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/setup.sh -------------------------------------------------------------------------------- /src/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/DNCnormalize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/src/DNCnormalize.py -------------------------------------------------------------------------------- /src/Encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/src/Encoder.py -------------------------------------------------------------------------------- /src/XGBclassify.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/src/XGBclassify.py -------------------------------------------------------------------------------- /src/classification_report.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/src/classification_report.py -------------------------------------------------------------------------------- /src/lib/access.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/src/lib/access.py -------------------------------------------------------------------------------- /src/lib/addressing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/src/lib/addressing.py -------------------------------------------------------------------------------- /src/lib/dnc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/src/lib/dnc.py -------------------------------------------------------------------------------- /src/lib/seq2seq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/src/lib/seq2seq.py -------------------------------------------------------------------------------- /src/lib/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/src/lib/util.py -------------------------------------------------------------------------------- /src/preprocessing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/src/preprocessing.py -------------------------------------------------------------------------------- /src/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cognibit/Text-Normalization-Demo/HEAD/src/utils.py --------------------------------------------------------------------------------