C1_W4_Assignment 3.6 Creating all hash tables

Course Q&A Natural Language Processing NLP with Classification and Vector Spaces
1

In section 3.6, the text says:

3.6 Creating all hash tables

You can now hash your vectors and store them in a hash table that would allow you to quickly look up and search for similar vectors. Run the cell below to create the hashes. By doing so, you end up having several tables which have all the vectors. Given a vector, you then identify the buckets in all the tables. You can then iterate over the buckets and consider much fewer vectors. The more buckets you use, the more accurate your lookup will be, but also the longer it will take.

However, I think the buckets in the statement is wrong. Instead, it should be more universes. Each universe has N buckets, and the more buckets you use, the less accurate your lookup is because you are comparing to a smaller set of candidates, thus the shorter it will take. But if you have more universes, the more accurate your lookup will be, and the longer it will take.

2

Hi Longyu_Zhao,

Thanks for reporting this!

It seems to me that the statement aimed to indicate something along the lines of “The more buckets you have to iterate over, the more accurate your lookup will be, but also the longer it will take”.

As the term ‘tables’ is used here rather than ‘universes’, I will suggest to people working on the backend to replace the term ‘buckets’ with ‘tables’, as in “The more tables you use, …”.