Classifying 19th Century British Library books using Crowdsourcing and Machine Learning

Introduction

Genre Classification

Overview of the Project: Classifying British Library Books By Genre
Genre Classification
Crude Genre Classification

Exploratory Data Analysis

Sample Inspector (Part I)
Sample Inspector (Part II)

Training our first model

Training our first book genre classification model
Model inference

Assesing our models performance

Improving our model
Assessing Where our Model is Going Wrong

Improving our model

Creating More Training Data Without More Annotating
Using our newly expanded data
Fine tuning our fastai model with new data
Using a Transformer Based Model

Sharing our results and final inference

Sharing our work
Using our new Hugging Face model

Further resources

Other resources
Bibliography
Glossary

Powered by Jupyter Book

Glossary

Glossary¶

Microsoft Digitised Books¶: TODO Add glossary for MS books
crowdsourcing¶: TODO add definition

previous

Bibliography

By Daniel van Strien, Giorgia Tolfo, Victoria Morris, Kaspar Beelen
© Copyright 2021 The Alan Turing Institute, British Library Board, Queen Mary University of London, University of Exeter, University of East Anglia and University of Cambridge..