Book Image

Machine Learning Solutions

Book Image

Machine Learning Solutions

Overview of this book

Machine learning (ML) helps you find hidden insights from your data without the need for explicit programming. This book is your key to solving any kind of ML problem you might come across in your job. You’ll encounter a set of simple to complex problems while building ML models, and you'll not only resolve these problems, but you’ll also learn how to build projects based on each problem, with a practical approach and easy-to-follow examples. The book includes a wide range of applications: from analytics and NLP, to computer vision domains. Some of the applications you will be working on include stock price prediction, a recommendation engine, building a chat-bot, a facial expression recognition system, and many more. The problem examples we cover include identifying the right algorithm for your dataset and use cases, creating and labeling datasets, getting enough clean data to carry out processing, identifying outliers, overftting datasets, hyperparameter tuning, and more. Here, you'll also learn to make more timely and accurate predictions. In addition, you'll deal with more advanced use cases, such as building a gaming bot, building an extractive summarization tool for medical documents, and you'll also tackle the problems faced while building an ML model. By the end of this book, you'll be able to fine-tune your models as per your needs to deliver maximum productivity.
Table of Contents (19 chapters)
Machine Learning Solutions
Foreword
Contributors
Preface
Index

Summary


In this chapter, we built the summarization application for medical transcriptions. In the beginning, we listed the challenges in order to generate a good parallel corpus for the summarization task in the medical domain. After that, for our baseline approach, we used the already available Python libraries, such as PyTeaser and Sumy. In the revised approach, we used word frequencies to generate the summary of the medical document. In the best possible approach, we combined the word frequency-based approach and the ranking mechanism in order to generate a summary for medical notes.

In the end, we developed a solution, where we used Amazon's review dataset, which is the parallel corpus for the summarization task, and we built the deep learning-based model for summarization. I would recommend that researchers, community members, and everyone else come forward to build high-quality datasets that can be used for building some great data science applications for the health and medical domains...