AI Practioner: Practical BERT Examples


Overview/Description
Expected Duration
Lesson Objectives
Course Number
Expertise Level



Overview/Description

Bidirectional Encoder Representations from Transformers (BERT) can be implemented in various ways, and it is up to AI practitioners to decide which one is the best for a particular product. It is also essential to recognize all of BERT's capabilities and its full potential in NLP.

In this course, you'll outline the theoretical approaches to several BERT use cases before illustrating how to implement each of them. In full, you'll learn how to use BERT for search engine optimization, sentence prediction, sentence classification, token classification, and question answering, implementing a simple example for each use case discussed. Lastly, you'll examine some fundamental guidelines for using BERT for content optimization.



Expected Duration (hours)
0.9

Lesson Objectives

AI Practioner: Practical BERT Examples

  • discover the key concepts covered in this course
  • name practical approaches to improving search using BERT
  • describe how BERT functions inside a search engine
  • demonstrate how BERT can be used to search the text of a given document
  • describe how we can use BERT for next sentence prediction
  • use BERT and Python for next sentence prediction via a PyTorch implementation of BERT
  • outline how BERT can be used for sequence classification
  • work with BERT to implement a sequence classifier
  • describe how multiple-choice reading comprehension can be done using BERT
  • use BERT and Python to implement multiple choice examples via a PyTorch implementation of BERT
  • outline how to utilize BERT for token classification
  • work with BERT to implement a token classifier
  • describe how to develop a question-answering machine using BERT
  • work with BERT to implement a question-answering machine
  • outline some fundamental guidelines for content optimization using BERT
  • summarize the key concepts covered in this course
  • Course Number:
    it_aibtbpdj_02_enus

    Expertise Level
    Expert