Chetna KhannainTowards Data ScienceWordPiece: Subword-based tokenization algorithmUnderstand subword-based tokenization algorithm used by state-of-the-art NLP models — WordPiece6 min read·Aug 18, 2021--1--1
Chetna KhannainTowards Data ScienceByte-Pair Encoding: Subword-based tokenization algorithmUnderstand subword-based tokenization algorithm used by state-of-the-art NLP models — Byte-Pair Encoding (BPE)9 min read·Aug 13, 2021--7--7
Chetna KhannainTowards Data ScienceWord, Subword, and Character-Based Tokenization: Know the DifferenceThe differences that anyone working on an NLP project should know8 min read·Jul 1, 2021--2--2
Chetna KhannainTowards Data ScienceUse the Datasets library of Hugging Face in your next NLP projectA quick guide to use Hugging Face’s datasets library!8 min read·Jun 9, 2021----
Chetna KhannainTowards Data ScienceQuestion Answering with a fine-tuned BERT11 min read·May 16, 2021--8--8
Chetna KhannaBar Chart or Histogram ?They look so alike, yet so different. Let’s find out the differences!5 min read·Apr 26, 2021----
Chetna KhannainTowards Data ScienceSampling Techniques in StatisticsA light introduction to different sampling techniques in statistics7 min read·Apr 14, 2021--1--1
Chetna KhannainTowards Data ScienceCIFAR 100: Transfer Learning using EfficientNetTransfer learning using state-of-the-art EfficientNet-B010 min read·Mar 30, 2021--2--2
Chetna KhannainTowards Data ScienceText pre-processing: Stop words removal using different librariesA handy guide about English stop words removal in Python!12 min read·Feb 10, 2021--4--4
Chetna KhannainTowards Data ScienceNull and Alternate Hypothesis… in simple plain English! Let’s get the basics clear.6 min read·Jan 31, 2021--2--2