First, your project is very useful for college students and it worths further development. However, there is something you can do better or you should reconsider about your project.
For the README part, I failed to learn how to generate the proper input of certain program, such as how to pre-process the document by Word2Vec, as you mentioned in the presentation. More specific steps are needed in order to let people know how to use it properly.
For the sprint 2, which uses a ''Extractive'' approach. Your work uses Word2Vec to pre-process the text that being tested, then uses TextRank API to simply pick out the highest ranking content. It is very easy though, it could not give a precise answer, the result might be consist of some useless contents and fail
to extract the REAL WORDS that are more constructive for users.
Anyway, using Machine Learning tool is worthy trying. Hope to see great progress in you guys Sprint 3.
First, your project is very useful for college students and it worths further development. However, there is something you can do better or you should reconsider about your project. For the README part, I failed to learn how to generate the proper input of certain program, such as how to pre-process the document by Word2Vec, as you mentioned in the presentation. More specific steps are needed in order to let people know how to use it properly. For the sprint 2, which uses a ''Extractive'' approach. Your work uses Word2Vec to pre-process the text that being tested, then uses TextRank API to simply pick out the highest ranking content. It is very easy though, it could not give a precise answer, the result might be consist of some useless contents and fail to extract the REAL WORDS that are more constructive for users. Anyway, using Machine Learning tool is worthy trying. Hope to see great progress in you guys Sprint 3.