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 ...

Get Machine Learning Solutions now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.