Building the baseline approach
In this section, we will be implementing the baseline approach for the summarization application. We will be using medical transcriptions to generate the summary. Here we will be using a small trial MIMIC-II dataset which contains a few sample medical documents and www.mtsamples.com for getting medical transcriptions. You can find the code by using this GitHub link: https://github.com/jalajthanaki/medical_notes_extractive_summarization/tree/master/Base_line_approach.
Let's start building the baseline approach.
Implementing the baseline approach
Here, we will be performing the following steps in order to build the baseline approach:
Install python dependencies
Write code and generate summary
Installing python dependencies
We will be using two python dependencies, which are really easy to use, in order to develop the summarization application. One is PyTeaser
, and the second one is Sumy
. You need to execute the following commands in order to install these two dependencies...