In Natural Language Processing (NLP), Entity Recognition is one of the common problems. The entity is referred to as the part of the text that one is interested in. In NLP, NER is a method of extracting the relevant information from a large corpus and classifying those entities into predefined categories such as: location, organization, name and so on.
-
geo--> Geographical Entity
-
org--> Organization
-
per--> Person
-
gpe--> Geopolitical Entity
-
tim--> Time indicator
-
art--> Artifact
-
eve--> Event
-
nat--> Natural Phenomenon
(https://www.kaggle.com/abhinavwalia95/entity-annotated-corpus)
- Preprocess text data
- Build and train Flair Model: Bi-directional LSTM and CRF
- Glove Embedding
- Stacked Embeddings: Glove, forward and backward Flair embeddings
- Evaluate our model on the test set
- Run the model on your own sentences!
All the code and comments are listed in the jupyter notbook (NER model file.ipynb)