This is a simple Named Entity Recognition (NER) tool that uses the ChatGPT language model provided by OpenAI. The purpose of this tool is to demonstrate that ChatGPT is good enough to use as an NER model and in some cases can be better than heuristic rule-based models.
Named Entity Recognition is a subtask of information extraction that involves identifying and classifying named entities in unstructured text into predefined categories such as person names, organizations, locations, and others.
Install the required packages by running the following command:
$ pip install -r requirements.txt
$ gradio app.py
The tool uses the ChatGPT API to predict the named entities in the input data and labels.
The output of the tool is a sequence of tokens with their corresponding predicted label. The tool then shows the output as table.
In conclusion, this simple NER tool demonstrates that ChatGPT is good enough to use as an NER model and sometimes better than heuristic rule-based models. However, it should be noted that the performance of the model heavily depends on the quality and quantity of the optimizing the prompt.