anwesham's picture
Update README.md
2038bb8

AI4Bharat's IndicBERT finetuned for few-shot transfer learning by fine-tuning on Hindi training data with Urdu validation and test sets. Expected low accuracy. Leverages mbert's tokenizer in this implementation.


language: - ur tags: - named entity recognition - ner license: apache-2.0 datasets: - wikiann metrics: - f1 - recall - precision - accuracy