CS410 Final Project - Tweet Normalizer

The Tweet Normalizer is the implementation of the unconstrained mode of this paper: NCSU-SAS-Ning: Candidate Generation and Feature Engineering for Supervised Lexical Normalization. Tweets are retrieved by the Twitter API /statuses/filter on the account @TestNormalizer specifically registered for this application. With the training on the dataset provided by this competition, and static mapping expanded by Lexical normalization dictionary (found in Resource section in the competition). The application supplies the revision feature, which expands the dataset to enable better normalization.