Your cart is empty.
Keep shoppingData Augmentation in NLP
24,550 students
Data Augmentation in NLP
Augment your Dataset and Outperform
Created byPrathamesh Dahale
Last updated 12/2020
English
What you'll learn
- Data Augmentation using Word Embeddings
- Data Augmentation using Word Embeddings - Implementation
- Data Augmentation using BERT
- Data Augmentation using BERT - Implementation
- Data Augmentation using Back Translation
- Data Augmentation using Back Translation - Implementation
- Data Augmentation using T5
- Data Augmentation using T5 - Implementation
- Improving Quality of Augmented Data using Similarity Filter
- Ensemble Approach for Data Augmentation
- Comparison of Data Augmentation Techniques
Explore related topics
Course content
7 sections • 12 lectures • 51m total length
Requirements
- Basic knowledge of machine learning and NLP is good to have
Description
You might have optimal machine learning algorithm to solve your problem. But once you apply it in real world soon you will realize that you need to train it on more data. Due to lack of large dataset you will try to further optimize the algorithm, tune hyper-parameters or look for some low tech approach. Most state of the art machine learning models are trained on large datasets. Real world performance of machine learning solutions drastically improves with more data.
Through this course you will learn multiple techniques for augmenting text data. These techniques can be used to generate data for any NLP task. This augmented dataset can help you to bridge the gap and quickly improve accuracy of your machine learning solutions.
Who this course is for:
- Anyone interested in machine learning and NLP.