Errata

Errata for Applied Natural Language Processing in the Enterprise

The errata list is a list of errors and their corrections that were found after the product was released. If the error was corrected in a later version or reprint the date of the correction will be displayed in the column titled "Date Corrected".

The following errata were submitted by our customers and approved as valid errors by the author or editor.

Color key: Serious technical mistake Minor technical mistake Language or formatting error Typo Question Note Update

Version Location Description Submitted By Date submitted Date corrected
Page 1
1

Sorry, I don't know the page number or para because I'm using O'Reilly Learning, but the error is here:

import spacy

import spacy

en_core_web_trf is the name of the dataset loaded earlier in the chapter.

Note from the Author or Editor:
Yes, let's change this to nlp = spacy.load("en_core_web_trf") on page 20 of the book to make this consistent with the download of "en_core_web_trf" on page 19.

Adam Witwer  Jul 07, 2021  Dec 10, 2021
Page 137
last paragraph

"The mathematical formulation for the simple RNN cell computation is:"
h_t+1 = tanh (W_ih*x_t + b_ih + W_hh*h_t + b_hh

shouldn't x_t be x_t+1?

look at this formula from the official documentations:
https://pytorch.org/docs/stable/generated/torch.nn.RNN.html
h_t​=tanh(Wih*​x_t​+b_ih​+W_hh*​h_(t−1)​+b_hh​)

furthermore, right below, the book says:
"...and hh means “hidden to input”"

shouldn't it be hidden to hidden, since it is a square matrix which has the size of the hidden layer?

Thanks for this precious book, I'm really enjoying it.

Note from the Author or Editor:
Both modifications are accurate.

The first equation in chapter 6 should be updated to match https://pytorch.org/docs/stable/generated/torch.nn.RNN.html and the second equation should be h_t​ = \tanh(Wih*​x_t​+b_ih​+W_hh*​h_(t−1)​+b_hh​)

The sentence below should read "and hh means “hidden to input”", as suggested.

gianni  Oct 17, 2021  Dec 10, 2021