Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

format fixes #4

Merged
merged 1 commit into from
Jan 5, 2022
Merged

format fixes #4

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 14 additions & 8 deletions genre_classification_of_bl_books/01_BL_fiction_non_fiction.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -938,9 +938,6 @@
"cell_type": "markdown",
"metadata": {
"id": "MoJ75jeVhsfn",
"jupyter": {
"source_hidden": true
},
"tags": []
},
"source": [
Expand Down Expand Up @@ -976,15 +973,25 @@
"\n",
"As a model gets better at performing this task it develops a representation of language which can be useful for other downstream tasks. \n",
"\n",
"For our starting point we will follow the 'ULMFIT' (Universal Language Model Fine Tuning) approach.\n",
"\n",
"For our starting point we will follow the 'ULMFIT' (Universal Language Model Fine Tuning) approach."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"```{image} https://www.novetta.com/wp-content/uploads/2019/02/ODSC-Blog.png\n",
":alt: aIllustration of the ulmfit approach\n",
":class: bg-primary mb-1\n",
":width: 500px\n",
":align: center\n",
"```\n",
"\n",
"```"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"As we can see from the illustration we'll start with a language model which has been trained on a general language modeling task, in this case on English Wikipedia articles. We'll then 'fine-tune' this model on all of our title data (our target domain). Through this process our language model should get better at 'understanding' what the book titles in our corpus looks like. In a later stage we will then use our fine tuned language model to create a classifier. "
]
},
Expand Down Expand Up @@ -3013,7 +3020,6 @@
"base_uri": "https://localhost:8080/",
"height": 1000
},
"collapsed": true,
"id": "1l404x-92oI7",
"jupyter": {
"outputs_hidden": true
Expand Down