Three different files for the following three tasks

1. Fill in key words: TourMegaEntityFiller.ipynb, ouput in filled_data.csv
2. Generate similar questions: TourMegaGenerateSimilar.ipynb, output in SemanticSimilar.csv
3. Map user question to similar question in dataset: TourMegaSimilarity.ipynb

*** To run any of the three files, simply import the CSV indicated by what is read in pd.read_csv, and run all the cells. You might have to restart the environment after pip installing the transformer libraries, but try to just run it directly first.

These are very initial versions of what I would do for these problems, but I wanted to get this in and show you my code! The final results will be better for 2. if the full system was implemented where entities were already filled, but I wanted to show each of the three systems in isolation on the original data.