NER-using-LSTM

Named Entity Recognition problem

Dataset: Entity Annotated Corpus

• The dataset contains text data that has been annotated with entity labels. This type of annotation is commonly used in natural language processing (NLP) tasks, particularly for tasks like named entity recognition (NER) where entities such as persons, organizations, locations, etc., need to be identified and classified within the text.
• Link: https://www.kaggle.com/datasets/abhinavwalia95/entity-annotated-corpus

Thanks for Fakhre Alam and Snehal Nair helped me alot with model architecture defining

• Fakhre Alam: https://www.youtube.com/watch?v=wr3C00RBgwk
• Snehal Nair: https://towardsdatascience.com/named-entity-recognition-ner-using-keras-bidirectional-lstm-28cd3f301f54

Performance:

• Training: loss: 0.0160 - accuracy: 0.9947
• Validation: loss: 0.0501 - accuracy: 0.9867
• Testing: loss: 0.0517 - accuracy: 0.9863