|
--- |
|
tags: |
|
- multimodal-entailment |
|
- generic |
|
|
|
--- |
|
## Tensorflow Keras Implementation of Named Entity Recognition using Transformers. |
|
|
|
This repo contains code using the model. [Named Entity Recognition using Transformers](https://keras.io/examples/nlp/ner_transformers/). |
|
|
|
Credits: [Varun Singh](https://www.linkedin.com/in/varunsingh2/) - Original Author |
|
|
|
HF Contribution: [Rishav Chandra Varma](https://huggingface.co/reichenbach) |
|
|
|
## Background Information |
|
|
|
### Introduction |
|
|
|
Named Entity Recognition (NER) is the process of identifying named entities in text. Example of named entities are: "Person", "Location", "Organization", "Dates" etc. NER is essentially a token classification task where every token is classified into one or more predetermined categories. |
|
|
|
We will train a simple Transformer based model to perform NER. We will be using the data from CoNLL 2003 shared task. For more information about the dataset, please visit the [dataset website](https://www.clips.uantwerpen.be/conll2003/ner/). However, since obtaining this data requires an additional step of getting a free license, we will be using HuggingFace's datasets library which contains a processed version of this [dataset](https://huggingface.co/datasets/conll2003). |
|
|
