This repo consists of different ways of extracting key-phrases from a sample text file. It includes some Python scripts that I wrote to learn about AWS services and applied NLP from open-source projects like spacy. It also includes a simple C# console app to help me learn about Azure key-phrase extraction API provided by Cognitive Services as well as learning about basic network REST API calls in C#.
I'm planning on continuing to explore AWS services like DynamoDB, ElasticSearch (to search amongst key-phrases), S3 (to store text-files and later store the link of each file in DynamoDB), and SQS to separate this key-phrase generating process into multiple services.
I'm also planning on specifying the domain of the key-phrases so that it helps me to learn and train my own NLP to recognize key-phrases in a specific context given that the input files are from this specific area. For example, I could pivot this project to extract keywords in the area of biomedical research paper to help doctors to identify the key ideas in the paper faster.