YelpDataChallenge

This is the project for Yelp Data Challenge

Clean text

1. Do we need to translate numbers into words
2. How to deal with some unmeaningful words in English, such as yammmmmm and Yummmmmmmmmmmmmmmmmmmmm? remove it or not?
3. how do the computer check this kind of sentence "We do n't have pizza like this in Hawaii , unfortunately". I think we need to convert this sentence to its standard form like this one "We do not have pizza like this in Hawaii , unfortunately".

Resource

1. Summarization MEAD
2. CS224d project reports
3. Sentence Extraction for Yelp Review Summarization
4. Learning Sentence Vector Representations to Summarize Yelp Reviews
5. NLP Structure
6. TextRank
7. Multi-document extraction based Summarization